Merge pull request 'development' (#27) from development into main

Reviewed-on: bandit/support-claude-mktplace#27
2026-01-19 22:23:28 +00:00
parent 1e63de6679 deae9a71d0
commit 3c3b9329c5
42 changed files with 3809 additions and 4545 deletions
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -1,7 +1,7 @@
 {
  "name": "bandit-claude-marketplace",
-  "version": "1.0.0",
+  "version": "2.0.0",
-  "description": "Project management plugins with Gitea, Wiki.js, and NetBox integrations",
+  "description": "Project management plugins with Gitea and NetBox integrations",
  "owner": {
    "name": "Bandit Labs",
    "email": "dev@banditlabs.io"
@@ -9,8 +9,8 @@
  "plugins": [
    {
      "name": "projman",
-      "version": "0.1.0",
+      "version": "2.0.0",
-      "description": "Sprint planning and project management with Gitea and Wiki.js integration",
+      "description": "Sprint planning and project management with Gitea integration",
      "source": "./plugins/projman"
    },
    {
@@ -24,6 +24,12 @@
      "version": "1.0.0",
      "description": "NetBox CMDB integration for infrastructure management",
      "source": "./plugins/cmdb-assistant"
    },
    {
      "name": "claude-config-maintainer",
      "version": "1.0.0",
      "description": "CLAUDE.md optimization and maintenance for Claude Code projects",
      "source": "./plugins/claude-config-maintainer"
    }
  ]
 }
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -4,14 +4,16 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 ## Project Overview
-This repository contains development of two Claude Code plugins for project management:
+This repository contains Claude Code plugins for project management:
-1. **`projman`** - Single-repository project management plugin (build first)
+1. **`projman`** - Single-repository project management plugin with Gitea integration
-2. **`projman-pmo`** - Multi-project PMO coordination plugin (build second)
+2. **`projman-pmo`** - Multi-project PMO coordination plugin
 3. **`claude-config-maintainer`** - CLAUDE.md optimization and maintenance plugin
 4. **`cmdb-assistant`** - NetBox CMDB integration for infrastructure management
-These plugins transform a proven 15-sprint workflow into reusable, distributable tools for managing software development with Claude Code, Gitea, Wiki.js, and agile methodologies.
+These plugins transform a proven 15-sprint workflow into reusable, distributable tools for managing software development with Claude Code, Gitea, and agile methodologies.
-**Status:** Planning phase complete, ready for implementation (Phase 1)
+**Status:** projman v1.0.0 complete with full Gitea integration
 ## File Creation Governance
@@ -38,8 +40,7 @@ Only these directories may exist at the repository root:
 | `.scratch/` | Transient work (auto-cleaned) |
 | `docs/` | Documentation |
 | `hooks/` | Shared hooks (if any) |
-| `mcp-servers/` | Shared MCP servers |
+| `plugins/` | All plugins (projman, projman-pmo, project-hygiene, cmdb-assistant, claude-config-maintainer) |
 | `plugins/` | All plugins (projman, projman-pmo, project-hygiene, cmdb-assistant) |
 | `scripts/` | Setup and maintenance scripts |
 ### File Creation Rules
@@ -97,7 +98,7 @@ Before creating any file, verify:
 ### Relative Path Rules
- Plugin to MCP server: `${CLAUDE_PLUGIN_ROOT}/../../mcp-servers/{server}`
+- Plugin to bundled MCP server: `${CLAUDE_PLUGIN_ROOT}/mcp-servers/{server}`
 - Marketplace to plugin: `./../../../plugins/{plugin-name}`
 - **ALWAYS calculate from CANONICAL-PATHS.md, never from memory**
@@ -139,9 +140,9 @@ The plugins implement a three-agent architecture that mirrors the proven workflo
 ### MCP Server Integration
-Both plugins use **two shared MCP servers** at repository root level (`mcp-servers/`):
+**Gitea MCP Server** (Python) - bundled in projman plugin
-**1. Gitea MCP Server** (Python)
+**Issue Tools:**
 - `list_issues` - Query issues with filters
 - `get_issue` - Fetch single issue details
 - `create_issue` - Create new issue with labels
@@ -150,20 +151,32 @@ Both plugins use **two shared MCP servers** at repository root level (`mcp-serve
 - `get_labels` - Fetch org + repo label taxonomy
 - `suggest_labels` - Analyze context and suggest appropriate labels
-**2. Wiki.js MCP Server** (Python, GraphQL)
+**Milestone Tools:**
- `search_pages` - Search Wiki.js pages by keywords/tags
+- `list_milestones` - List sprint milestones
- `get_page` - Fetch specific page content
+- `get_milestone` - Get milestone details
- `create_page` - Create new Wiki page
+- `create_milestone` - Create sprint milestone
- `update_page` - Modify existing page
+- `update_milestone` - Update/close milestone
- `list_pages` - List pages in a path
+
 **Dependency Tools:**
 - `list_issue_dependencies` - Get issue dependencies
 - `create_issue_dependency` - Create dependency between issues
 - `get_execution_order` - Get parallel execution batches
 **Wiki Tools (Gitea Wiki):**
 - `list_wiki_pages` - List wiki pages
 - `get_wiki_page` - Fetch specific page content
 - `create_wiki_page` - Create new wiki page
 - `create_lesson` - Create lessons learned document
 - `search_lessons` - Search past lessons by tags
- `tag_lesson` - Add tags to lessons learned
+
 **Validation Tools:**
 - `validate_repo_org` - Check repo belongs to organization
 - `get_branch_protection` - Check branch protection rules
 - `create_label` - Create missing required labels
 **Key Architecture Points:**
 - MCP servers are **bundled inside each plugin** at `plugins/{plugin}/mcp-servers/`
 - This ensures plugins work when cached by Claude Code (only plugin directory is cached)
 - Each MCP server detects its mode (project-scoped vs company-wide) based on environment variables
 - Configuration uses hybrid approach (system-level + project-level)
 - All plugins reference `${CLAUDE_PLUGIN_ROOT}/mcp-servers/` in their `.mcp.json` files
@@ -213,36 +226,15 @@ The label system includes:
 **Critical Feature:** After 15 sprints without lesson capture, repeated mistakes occurred (e.g., Claude Code infinite loops on similar issues 2-3 times).
-**Wiki.js Structure (Example):**
+**Gitea Wiki Structure:**
-```
+Lessons learned are stored in the Gitea repository's built-in wiki under `lessons-learned/sprints/`.
 Wiki.js: https://wiki.your-company.com
 └── /your-org/
    ├── projects/                       # Project-specific documentation
    │   ├── project-a/
    │   │   ├── lessons-learned/
    │   │   │   ├── sprints/
    │   │   │   ├── patterns/
    │   │   │   └── INDEX.md
    │   │   └── documentation/
    │   ├── project-b/
    │   └── project-c/
    ├── company/                        # Company-wide documentation
    │   ├── processes/
    │   ├── standards/
    │   └── tools/
    └── shared/                         # Cross-project resources
        ├── architecture-patterns/
        ├── best-practices/
        └── tech-stack/
 ```
 **Workflow:**
- Orchestrator captures lessons at sprint close via Wiki.js MCP
+- Orchestrator captures lessons at sprint close via Gitea Wiki MCP tools
- Planner searches relevant lessons at sprint start using GraphQL search
+- Planner searches relevant lessons at sprint start using `search_lessons`
 - INDEX.md maintained automatically via Wiki.js API
 - Tags enable cross-project lesson discovery
 - Focus on preventable repetitions, not every detail
- Web interface for team review and editing
+- Web interface available through Gitea Wiki
 ## Development Workflow
@@ -268,12 +260,7 @@ bandit/support-claude-mktplace/
 │   │   │   └── plugin.json
 │   │   ├── .mcp.json               # Points to ${CLAUDE_PLUGIN_ROOT}/mcp-servers/
 │   │   ├── mcp-servers/            # ← MCP servers BUNDLED IN plugin
-│   │   │   ├── gitea/
+│   │   │   └── gitea/              # Gitea + Wiki tools
 │   │   │   │   ├── .venv/
 │   │   │   │   ├── requirements.txt
 │   │   │   │   ├── mcp_server/
 │   │   │   │   └── tests/
 │   │   │   └── wikijs/
 │   │   │       ├── .venv/
 │   │   │       ├── requirements.txt
 │   │   │       ├── mcp_server/
@@ -283,7 +270,8 @@ bandit/support-claude-mktplace/
 │   │   │   ├── sprint-start.md
 │   │   │   ├── sprint-status.md
 │   │   │   ├── sprint-close.md
-│   │   │   └── labels-sync.md
+│   │   │   ├── labels-sync.md
 │   │   │   └── initial-setup.md
 │   │   ├── agents/
 │   │   │   ├── planner.md
 │   │   │   ├── orchestrator.md
@@ -323,12 +311,10 @@ bandit/support-claude-mktplace/
 ### Key Design Decisions
 **MCP Servers (Bundled in Plugins):**
- **Gitea MCP**: Issues, labels, repository management (bundled in projman)
+- **Gitea MCP**: Issues, labels, wiki, milestones, dependencies (bundled in projman)
 - **Wiki.js MCP**: Documentation, lessons learned, knowledge base (bundled in projman)
 - **NetBox MCP**: Infrastructure management (bundled in cmdb-assistant)
 - Servers are **bundled inside each plugin** that needs them
 - This ensures plugins work when cached by Claude Code
 - Mode detection based on environment variables (project vs company-wide)
 **Python Implementation:**
 - Python chosen over Node.js for MCP servers
@@ -337,8 +323,8 @@ bandit/support-claude-mktplace/
 - Virtual environment (.venv) per MCP server
 **Hybrid Configuration:**
- **System-level**: `~/.config/claude/gitea.env` and `wikijs.env` (credentials)
+- **System-level**: `~/.config/claude/gitea.env` (credentials)
- **Project-level**: `project-root/.env` (repository and path specification)
+- **Project-level**: `project-root/.env` (repository specification)
 - Merge strategy: project overrides system
 - Benefits: Single token per service, easy multi-project setup
@@ -370,9 +356,9 @@ PMO plugin adds:
 - Company-wide lessons learned search
 **Configuration Difference:**
- PMO operates at company level (no `GITEA_REPO` or `WIKIJS_PROJECT`)
+- PMO operates at company level (no `GITEA_REPO`)
- Accesses entire organization Wiki.js namespace
+- Accesses all repositories in organization
- Queries all repositories in organization
+- Aggregates issues and lessons across projects
 Build PMO plugin AFTER projman is working and validated.
@@ -405,7 +391,7 @@ Test in a real repository with actual Gitea instance before distribution.
 - **Type/Refactor label** - Newly implemented at org level for architectural work
 - **Branch detection must be 100% reliable** - Prevents production accidents
 - **Python for MCP servers** - Use Python 3.8+ with virtual environments
- **Wiki.js structure** - Organization content under configured base namespace
+- **CLI tools forbidden** - Use MCP tools exclusively, never CLI tools like `tea` or `gh`
 ## CRITICAL: Rules You MUST Follow
--- a/README.md
+++ b/README.md
@@ -1,20 +1,34 @@
 # Claude Code Marketplace - Bandit Labs
-A collection of Claude Code plugins and MCP servers for project management, infrastructure automation, and development workflows.
+A collection of Claude Code plugins for project management, infrastructure automation, and development workflows.
 ## Plugins
-### [projman](./plugins/projman/README.md)
+### [projman](./plugins/projman/README.md) v2.0.0
 **Sprint Planning and Project Management**
-AI-guided sprint planning with Gitea and Wiki.js integration. Transforms a proven 15-sprint workflow into a distributable plugin.
+AI-guided sprint planning with full Gitea integration. Transforms a proven 15-sprint workflow into a distributable plugin.
 - Three-agent model: Planner, Orchestrator, Executor
- Intelligent label suggestions from 44-label taxonomy
+- Intelligent label suggestions from 43-label taxonomy
- Lessons learned capture to prevent repeated mistakes
+- Lessons learned capture via Gitea Wiki
 - Native issue dependencies with parallel execution
 - Milestone management for sprint organization
 - Branch-aware security (development/staging/production)
-**Commands:** `/sprint-plan`, `/sprint-start`, `/sprint-status`, `/sprint-close`, `/labels-sync`
+**Commands:** `/sprint-plan`, `/sprint-start`, `/sprint-status`, `/sprint-close`, `/labels-sync`, `/initial-setup`
 ### [claude-config-maintainer](./plugins/claude-config-maintainer/README.md)
 **CLAUDE.md Optimization and Maintenance**
 Analyze, optimize, and create CLAUDE.md configuration files for Claude Code projects.
 - Structure and clarity scoring (100-point system)
 - Automatic optimization with preview and backup
 - Project-aware initialization with stack detection
 - Best practices enforcement
 **Commands:** `/config-analyze`, `/config-optimize`, `/config-init`
 ### [cmdb-assistant](./plugins/cmdb-assistant/README.md)
 **NetBox CMDB Integration**
@@ -35,41 +49,28 @@ Hook-based cleanup that runs after Claude completes work.
 - Deletes temp files (`*.tmp`, `*.bak`, `__pycache__`, etc.)
 - Warns about unexpected files in project root
- Identifies orphaned supporting files (`test_*`, `debug_*`, `*_backup.*`)
+- Identifies orphaned supporting files
 - Logs actions to `.dev/logs/`
 - Configurable via `.hygiene.json`
 **Hook:** `task-completed`
 ## MCP Servers
-Shared Model Context Protocol servers that provide plugins with external service access.
+MCP servers are **bundled inside each plugin** that needs them. This ensures plugins work when cached by Claude Code.
-### [Gitea MCP Server](./mcp-servers/gitea/README.md)
+### Gitea MCP Server (bundled in projman)
 Issue management, label operations, and repository tracking for Gitea.
-| Tool | Description |
+Full Gitea API integration for project management.
 |------|-------------|
 | `list_issues` | Query issues with filters |
 | `create_issue` | Create issue with labels |
 | `get_labels` | Fetch org + repo labels |
 | `suggest_labels` | Intelligent label suggestions |
-**Status:** Production Ready
+| Category | Tools |
 |----------|-------|
 | Issues | `list_issues`, `get_issue`, `create_issue`, `update_issue`, `add_comment` |
 | Labels | `get_labels`, `suggest_labels`, `create_label` |
 | Wiki | `list_wiki_pages`, `get_wiki_page`, `create_wiki_page`, `create_lesson`, `search_lessons` |
 | Milestones | `list_milestones`, `get_milestone`, `create_milestone`, `update_milestone` |
 | Dependencies | `list_issue_dependencies`, `create_issue_dependency`, `get_execution_order` |
 | Validation | `validate_repo_org`, `get_branch_protection` |
-### [Wiki.js MCP Server](./mcp-servers/wikijs/README.md)
+### NetBox MCP Server (bundled in cmdb-assistant)
 Documentation management and lessons learned capture via GraphQL.
 | Tool | Description |
 |------|-------------|
 | `search_pages` | Search by keywords/tags |
 | `create_page` | Create markdown pages |
 | `create_lesson` | Capture sprint lessons |
 | `search_lessons` | Find relevant insights |
 **Status:** Production Ready
 ### [NetBox MCP Server](./mcp-servers/netbox/README.md)
 Comprehensive NetBox REST API integration for infrastructure management.
 | Module | Coverage |
@@ -80,15 +81,13 @@ Comprehensive NetBox REST API integration for infrastructure management.
 | Virtualization | Clusters, VMs, Interfaces |
 | Extras | Tags, Custom Fields, Audit Log |
 **Status:** Production Ready
 ## Installation
 ### Prerequisites
 - Claude Code installed
 - Python 3.10+
- Access to target services (Gitea, Wiki.js, NetBox as needed)
+- Access to target services (Gitea, NetBox as needed)
 ### Quick Start
@@ -100,35 +99,33 @@ Comprehensive NetBox REST API integration for infrastructure management.
 2. **Install MCP server dependencies:**
   ```bash
-   # Gitea MCP
+   # Gitea MCP (for projman)
-   cd mcp-servers/gitea && python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
+   cd plugins/projman/mcp-servers/gitea
   python3 -m venv .venv
   source .venv/bin/activate
   pip install -r requirements.txt
   deactivate
-   # Wiki.js MCP
+   # NetBox MCP (for cmdb-assistant)
-   cd ../wikijs && python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
+   cd ../../../cmdb-assistant/mcp-servers/netbox
-
+   python3 -m venv .venv
-   # NetBox MCP
+   source .venv/bin/activate
-   cd ../netbox && python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
+   pip install -r requirements.txt
   deactivate
   ```
-3. **Configure credentials:**
+3. **Configure system-level credentials:**
   ```bash
   mkdir -p ~/.config/claude
-   # Gitea
+   # Gitea credentials
   cat > ~/.config/claude/gitea.env << 'EOF'
-   GITEA_API_URL=https://gitea.example.com/api/v1
+   GITEA_URL=https://gitea.example.com
-   GITEA_API_TOKEN=your_token
+   GITEA_TOKEN=your_token
-   GITEA_OWNER=your_org
+   GITEA_ORG=your_org
   EOF
-   # Wiki.js
+   # NetBox credentials
   cat > ~/.config/claude/wikijs.env << 'EOF'
   WIKIJS_API_URL=https://wiki.example.com/graphql
   WIKIJS_API_TOKEN=your_token
   WIKIJS_BASE_PATH=/your-namespace
   EOF
   # NetBox
   cat > ~/.config/claude/netbox.env << 'EOF'
   NETBOX_API_URL=https://netbox.example.com/api
   NETBOX_API_TOKEN=your_token
@@ -137,103 +134,81 @@ Comprehensive NetBox REST API integration for infrastructure management.
   chmod 600 ~/.config/claude/*.env
   ```
-4. **Add marketplace to Claude Code:**
+4. **Configure project-level settings:**
   ```bash
-   claude plugin marketplace add /path/to/support-claude-mktplace
+   # In your target project root
-   claude plugin install projman
+   cat > .env << 'EOF'
-   claude plugin install cmdb-assistant
+   GITEA_REPO=your-repository-name
-   claude plugin install project-hygiene
+   EOF
   ```
 5. **Add marketplace to Claude Code:**
   Add to your project's `.claude/settings.json`:
   ```json
   {
     "pluginMarketplace": "/path/to/support-claude-mktplace"
   }
   ```
 ## Repository Structure
 ```
 support-claude-mktplace/
-├── plugins/                    # All plugins
+├── .claude-plugin/                # Marketplace manifest
-│   ├── projman/               # Sprint management plugin
+│   └── marketplace.json
 ├── plugins/                       # All plugins (with bundled MCP servers)
 │   ├── projman/                   # Sprint management plugin
 │   │   ├── .claude-plugin/
 │   │   ├── .mcp.json
 │   │   ├── mcp-servers/           # Bundled MCP server
 │   │   │   └── gitea/
 │   │   ├── commands/
 │   │   ├── agents/
 │   │   └── skills/
-│   ├── projman-pmo/           # PMO coordination plugin
+│   ├── claude-config-maintainer/  # CLAUDE.md optimization plugin
 │   │   ├── .claude-plugin/
 │   │   ├── commands/
 │   │   └── agents/
-│   ├── project-hygiene/       # Cleanup automation plugin
+│   ├── cmdb-assistant/            # NetBox CMDB integration
 │   │   ├── .claude-plugin/
-│   │   └── hooks/
+│   │   ├── .mcp.json
-│   └── cmdb-assistant/        # NetBox CMDB integration
+│   │   ├── mcp-servers/           # Bundled MCP server
-│       ├── .claude-plugin/
+│   │   │   └── netbox/
-│       ├── commands/
+│   │   ├── commands/
-│       └── agents/
+│   │   └── agents/
-├── mcp-servers/               # Shared MCP servers
+│   ├── projman-pmo/               # PMO coordination plugin (planned)
-│   ├── gitea/
+│   └── project-hygiene/           # Cleanup automation plugin
-│   ├── wikijs/
+├── docs/                          # Reference documentation
-│   └── netbox/
+│   ├── CANONICAL-PATHS.md         # Single source of truth for paths
 ├── .claude-plugin/            # Marketplace manifest (bandit-claude-marketplace)
 │   └── marketplace.json
 ├── docs/                      # Reference documentation
 │   └── references/
-└── .claude/                   # Claude Code local settings
+└── scripts/                       # Setup and maintenance scripts
 ```
 ## Key Features (v2.0.0)
 ### Parallel Execution
 Tasks are batched by dependency graph for optimal parallel execution:
 ```
 Batch 1 (parallel): Task A, Task B, Task C
 Batch 2 (parallel): Task D, Task E  (depend on Batch 1)
 Batch 3 (sequential): Task F        (depends on Batch 2)
 ```
 ### Naming Conventions
 - **Tasks:** `[Sprint XX] <type>: <description>`
 - **Branches:** `feat/`, `fix/`, `debug/` prefixes with issue numbers
 ### CLI Tools Blocked
 All agents use MCP tools exclusively. CLI tools like `tea` or `gh` are forbidden to ensure consistent, auditable operations.
 ## Documentation
 ### Reference Material
 | Document | Description |
 |----------|-------------|
 | [PROJECT-SUMMARY.md](./docs/references/PROJECT-SUMMARY.md) | Architecture overview and design decisions |
 | [PLUGIN-PROJMAN.md](./docs/references/PLUGIN-PROJMAN.md) | Detailed projman plugin specification |
 | [PLUGIN-PMO.md](./docs/references/PLUGIN-PMO.md) | Multi-project PMO plugin specification |
 | [MCP-GITEA.md](./docs/references/MCP-GITEA.md) | Gitea MCP server API reference |
 | [MCP-WIKIJS.md](./docs/references/MCP-WIKIJS.md) | Wiki.js MCP server API reference |
 ### Testing & Validation
 | Document | Description |
 |----------|-------------|
 | [PROJMAN_TESTING_COMPLETE.md](./docs/PROJMAN_TESTING_COMPLETE.md) | Test results and validation |
 | [LIVE_API_TEST_RESULTS.md](./docs/LIVE_API_TEST_RESULTS.md) | Live API integration tests |
 | [TEST_EXECUTION_REPORT.md](./docs/TEST_EXECUTION_REPORT.md) | Full test execution report |
 ### Configuration Guides
 | Document | Description |
 |----------|-------------|
 | [CLAUDE.md](./CLAUDE.md) | Main project instructions |
 | [CANONICAL-PATHS.md](./docs/CANONICAL-PATHS.md) | Authoritative path reference |
 | [projman/CONFIGURATION.md](./plugins/projman/CONFIGURATION.md) | Projman setup guide |
 | [CREATE_LABELS_GUIDE.md](./docs/CREATE_LABELS_GUIDE.md) | Gitea label taxonomy setup |
 ## Development
 ### Adding New Plugins
 1. Create plugin directory in `plugins/` with `.claude-plugin/plugin.json`
 2. Add commands, agents, or hooks as needed
 3. Reference shared MCP servers via `.mcp.json` (use `../../mcp-servers/`)
 4. Add to marketplace in `.claude-plugin/marketplace.json`
 5. Document in plugin `README.md`
 ### Testing
 ```bash
 # MCP server unit tests
 cd mcp-servers/gitea && pytest -v
 cd mcp-servers/wikijs && pytest -v
 # Plugin validation
 claude plugin list
 claude --debug
 ```
 ## Roadmap
 - [x] **Phase 1-2**: MCP servers and commands (Complete)
 - [ ] **Phase 3**: Agent system implementation
 - [ ] **Phase 4**: Lessons learned integration
 - [ ] **Phase 5-8**: Testing, documentation, production
 - [ ] **Phase 9-11**: PMO plugin for multi-project coordination
 - [ ] **Phase 12**: Public marketplace distribution
 ## License
--- a/docs/CANONICAL-PATHS.md
+++ b/docs/CANONICAL-PATHS.md
@@ -23,17 +23,20 @@ support-claude-mktplace/
 │   ├── projman/
 │   │   ├── .claude-plugin/
 │   │   ├── mcp-servers/        # MCP servers bundled IN plugin
-│   │   │   ├── gitea/
+│   │   │   └── gitea/          # Gitea + Wiki tools
 │   │   │   └── wikijs/
 │   │   ├── commands/
 │   │   ├── agents/
 │   │   └── skills/
 │   ├── projman-pmo/
 │   ├── project-hygiene/
-│   └── cmdb-assistant/
+│   ├── cmdb-assistant/
 │   │   ├── .claude-plugin/
 │   │   ├── mcp-servers/        # MCP servers bundled IN plugin
 │   │   │   └── netbox/
 │   │   ├── commands/
 │   │   └── agents/
 │   └── claude-config-maintainer/
 │       ├── .claude-plugin/
 │       ├── mcp-servers/        # MCP servers bundled IN plugin
 │       │   └── netbox/
 │       ├── commands/
 │       └── agents/
 ├── scripts/                    # Setup and maintenance scripts
--- a/plugins/claude-config-maintainer/.claude-plugin/plugin.json
+++ b/plugins/claude-config-maintainer/.claude-plugin/plugin.json
@@ -0,0 +1,30 @@
 {
  "name": "claude-config-maintainer",
  "version": "1.0.0",
  "description": "Maintains and optimizes CLAUDE.md configuration files for Claude Code projects",
  "entryPoint": "agents/maintainer.md",
  "commands": [
    {
      "name": "config-analyze",
      "description": "Analyze CLAUDE.md for optimization opportunities",
      "entryPoint": "commands/analyze.md"
    },
    {
      "name": "config-optimize",
      "description": "Optimize CLAUDE.md structure and content",
      "entryPoint": "commands/optimize.md"
    },
    {
      "name": "config-init",
      "description": "Initialize a new CLAUDE.md file for a project",
      "entryPoint": "commands/init.md"
    }
  ],
  "agents": [
    {
      "name": "maintainer",
      "description": "CLAUDE.md optimization and maintenance agent",
      "entryPoint": "agents/maintainer.md"
    }
  ]
 }
--- a/plugins/claude-config-maintainer/README.md
+++ b/plugins/claude-config-maintainer/README.md
@@ -0,0 +1,99 @@
 # Claude Config Maintainer
 A Claude Code plugin for creating and maintaining optimized CLAUDE.md configuration files.
 ## Overview
 CLAUDE.md files provide instructions to Claude Code when working with a project. This plugin helps you:
 - **Analyze** existing CLAUDE.md files for improvement opportunities
 - **Optimize** structure, clarity, and conciseness
 - **Initialize** new CLAUDE.md files with project-specific content
 ## Installation
 This plugin is part of the support-claude-mktplace collection. Install the marketplace and the plugin will be available.
 ## Commands
 ### `/config-analyze`
 Analyze your CLAUDE.md and get a detailed report with scores and recommendations.
 ```
 /config-analyze
 ```
 ### `/config-optimize`
 Automatically optimize your CLAUDE.md based on best practices.
 ```
 /config-optimize
 ```
 ### `/config-init`
 Create a new CLAUDE.md tailored to your project.
 ```
 /config-init
 ```
 ## Best Practices
 A good CLAUDE.md should be:
 - **Clear** - Easy to understand at a glance
 - **Concise** - No unnecessary content
 - **Complete** - All essential information included
 - **Current** - Up to date with the project
 ### Recommended Structure
 ```markdown
 # CLAUDE.md
 ## Project Overview
 What does this project do?
 ## Quick Start
 Essential build/test/run commands.
 ## Critical Rules
 What must Claude NEVER do?
 ## Architecture (optional)
 Key technical decisions.
 ## Common Operations (optional)
 Frequent tasks and workflows.
 ```
 ### Length Guidelines
 | Project Size | Recommended Lines |
 |-------------|------------------|
 | Small | 50-100 |
 | Medium | 100-200 |
 | Large | 200-400 |
 ## Scoring System
 The analyzer scores CLAUDE.md files on:
 - **Structure** (25 pts) - Organization and navigation
 - **Clarity** (25 pts) - Clear, unambiguous instructions
 - **Completeness** (25 pts) - Essential sections present
 - **Conciseness** (25 pts) - Efficient information density
 Target score: **70+** for effective Claude Code usage.
 ## Tips
 1. Run `/config-analyze` periodically to maintain quality
 2. Update CLAUDE.md when adding major features
 3. Keep critical rules prominent and clear
 4. Include examples where they add clarity
 5. Remove generic advice that applies to all projects
 ## Contributing
 This plugin is part of the bandit/support-claude-mktplace repository.
--- a/plugins/claude-config-maintainer/agents/maintainer.md
+++ b/plugins/claude-config-maintainer/agents/maintainer.md
@@ -0,0 +1,279 @@
 ---
 name: maintainer
 description: CLAUDE.md optimization and maintenance agent
 ---
 # CLAUDE.md Maintainer Agent
 You are the **Maintainer Agent** - a specialist in creating and optimizing CLAUDE.md configuration files for Claude Code projects. Your role is to ensure CLAUDE.md files are clear, concise, well-structured, and follow best practices.
 ## Your Personality
 **Optimization-Focused:**
 - Identify redundancy and eliminate it
 - Streamline instructions for clarity
 - Ensure every section serves a purpose
 - Balance comprehensiveness with conciseness
 **Standards-Aware:**
 - Know Claude Code best practices
 - Understand what makes effective instructions
 - Follow consistent formatting conventions
 - Apply lessons learned from real usage
 **Proactive:**
 - Suggest improvements without being asked
 - Identify potential issues before they cause problems
 - Recommend structure changes when beneficial
 - Keep configurations up to date
 ## Your Responsibilities
 ### 1. Analyze CLAUDE.md Files
 When analyzing a CLAUDE.md file, evaluate:
 **Structure:**
 - Is the file well-organized?
 - Are sections logically ordered?
 - Is navigation easy?
 - Are headers clear and descriptive?
 **Content Quality:**
 - Are instructions clear and unambiguous?
 - Is there unnecessary repetition?
 - Are examples provided where helpful?
 - Is the tone appropriate (direct, professional)?
 **Completeness:**
 - Does it cover essential project information?
 - Are key workflows documented?
 - Are constraints and requirements clear?
 - Are critical rules highlighted?
 **Conciseness:**
 - Is information presented efficiently?
 - Can sections be combined or streamlined?
 - Are there verbose explanations that could be shortened?
 - Is the file too long for effective use?
 ### 2. Optimize CLAUDE.md Structure
 **Recommended Structure:**
 ```markdown
 # CLAUDE.md
 ## Project Overview
 Brief description of what this project does.
 ## Quick Start
 Essential commands to get started (build, test, run).
 ## Architecture
 Key technical decisions and structure.
 ## Important Rules
 CRITICAL constraints that MUST be followed.
 ## Common Operations
 Frequent tasks and how to perform them.
 ## File Structure
 Key directories and their purposes.
 ## Troubleshooting
 Common issues and solutions.
 ```
 **Key Principles:**
 - Most important information first
 - Group related content together
 - Use headers that scan easily
 - Include examples where they add clarity
 ### 3. Apply Best Practices
 **DO:**
 - Use clear, direct language
 - Provide concrete examples
 - Highlight critical rules with emphasis
 - Keep sections focused on single topics
 - Use bullet points for lists
 - Include "DO NOT" sections for common mistakes
 **DON'T:**
 - Write verbose explanations
 - Repeat information in multiple places
 - Include documentation that belongs elsewhere
 - Add generic advice that applies to all projects
 - Use emojis unless project requires them
 ### 4. Generate Improvement Reports
 After analyzing a CLAUDE.md, provide:
 ```
 CLAUDE.md Analysis Report
 =========================
 Overall Score: X/10
 Strengths:
 - Clear project overview
 - Good use of examples
 - Well-organized structure
 Areas for Improvement:
 1. Section "X" is too verbose (lines 45-78)
   Recommendation: Condense to key points
 2. Duplicate information in sections Y and Z
   Recommendation: Consolidate into single section
 3. Missing "Quick Start" section
   Recommendation: Add essential commands
 4. Critical rules buried in middle of document
   Recommendation: Move to prominent position
 Suggested Actions:
 1. [High Priority] Add Quick Start section
 2. [Medium Priority] Consolidate duplicate content
 3. [Low Priority] Improve header naming
 Would you like me to implement these improvements?
 ```
 ### 5. Create New CLAUDE.md Files
 When creating a new CLAUDE.md:
 1. **Gather Project Context**
   - What type of project (web app, CLI tool, library)?
   - What technologies are used?
   - What are the build/test/run commands?
   - What constraints should Claude follow?
 2. **Generate Tailored Content**
   - Project-specific instructions
   - Relevant quick start commands
   - Architecture appropriate to the stack
   - Rules specific to the codebase
 3. **Review and Refine**
   - Ensure nothing critical is missing
   - Verify instructions are accurate
   - Check for appropriate length
   - Confirm clear structure
 ## CLAUDE.md Best Practices
 ### Length Guidelines
 | Project Size | Recommended Length |
 |-------------|-------------------|
 | Small (< 10 files) | 50-100 lines |
 | Medium (10-100 files) | 100-200 lines |
 | Large (100+ files) | 200-400 lines |
 **Rule of thumb:** If you can't scan the document in 2 minutes, it's too long.
 ### Essential Sections
 Every CLAUDE.md should have:
 1. **Project Overview** - What is this?
 2. **Quick Start** - How do I build/test/run?
 3. **Important Rules** - What must I NOT do?
 ### Optional Sections (as needed)
 - Architecture (for complex projects)
 - File Structure (for large codebases)
 - Common Operations (for frequent tasks)
 - Troubleshooting (for known issues)
 - Integration Points (for systems with external dependencies)
 ### Formatting Rules
 - Use `##` for main sections, `###` for subsections
 - Use code blocks for commands and file paths
 - Use **bold** for critical warnings
 - Use bullet points for lists of 3+ items
 - Use tables for structured comparisons
 ### Critical Rules Section
 Format critical rules prominently:
 ```markdown
 ## CRITICAL: Rules You MUST Follow
 ### Never Do These Things
 - **NEVER** modify .gitignore without permission
 - **NEVER** commit secrets to the repository
 - **NEVER** run destructive commands without confirmation
 ### Always Do These Things
 - **ALWAYS** run tests before committing
 - **ALWAYS** use the virtual environment
 - **ALWAYS** follow the branching convention
 ```
 ## Communication Style
 **Be direct:**
 - Tell users exactly what to change
 - Provide specific line numbers when relevant
 - Show before/after comparisons
 **Be constructive:**
 - Frame improvements positively
 - Explain why changes help
 - Prioritize recommendations
 **Be practical:**
 - Focus on actionable improvements
 - Consider implementation effort
 - Suggest incremental changes when appropriate
 ## Example Optimization
 **Before (verbose):**
 ```markdown
 ## Running Tests
 In order to run the tests for this project, you will need to make sure
 that you have all the dependencies installed first. You can do this by
 running the pip install command. After that, you can run the tests using
 pytest. Make sure you're in the project root directory when you run
 these commands.
 To install dependencies:
 pip install -r requirements.txt
 To run tests:
 pytest
 ```
 **After (optimized):**
 ```markdown
 ## Testing
 ```bash
 pip install -r requirements.txt  # Install dependencies (first time only)
 pytest                           # Run all tests
 pytest tests/test_api.py -v      # Run specific file with verbose output
 ```
 ```
 ## Your Mission
 Help users create and maintain CLAUDE.md files that are:
 - **Clear** - Easy to understand at a glance
 - **Concise** - No unnecessary content
 - **Complete** - All essential information included
 - **Consistent** - Well-structured and formatted
 - **Current** - Up to date with the project
 You are the maintainer who ensures Claude Code has the best possible instructions to work with any project effectively.
--- a/plugins/claude-config-maintainer/commands/analyze.md
+++ b/plugins/claude-config-maintainer/commands/analyze.md
@@ -0,0 +1,132 @@
 ---
 description: Analyze CLAUDE.md for optimization opportunities
 ---
 # Analyze CLAUDE.md
 This command analyzes your project's CLAUDE.md file and provides a detailed report on optimization opportunities.
 ## What This Command Does
 1. **Read CLAUDE.md** - Locates and reads the project's CLAUDE.md file
 2. **Analyze Structure** - Evaluates organization, headers, and flow
 3. **Check Content** - Reviews clarity, completeness, and conciseness
 4. **Identify Issues** - Finds redundancy, verbosity, and missing sections
 5. **Generate Report** - Provides scored assessment with recommendations
 ## Usage
 ```
 /config-analyze
 ```
 Or invoke the maintainer agent directly:
 ```
 Analyze the CLAUDE.md file in this project
 ```
 ## Analysis Criteria
 ### Structure (25 points)
 - Logical section ordering
 - Clear header hierarchy
 - Easy navigation
 - Appropriate grouping
 ### Clarity (25 points)
 - Clear instructions
 - Good examples
 - Unambiguous language
 - Appropriate detail level
 ### Completeness (25 points)
 - Project overview present
 - Quick start commands documented
 - Critical rules highlighted
 - Key workflows covered
 ### Conciseness (25 points)
 - No unnecessary repetition
 - Efficient information density
 - Appropriate length for project size
 - No generic filler content
 ## Expected Output
 ```
 CLAUDE.md Analysis Report
 =========================
 File: /path/to/project/CLAUDE.md
 Lines: 245
 Last Modified: 2025-01-18
 Overall Score: 72/100
 Category Scores:
 - Structure:    20/25 (Good)
 - Clarity:      18/25 (Good)
 - Completeness: 22/25 (Excellent)
 - Conciseness:  12/25 (Needs Work)
 Strengths:
 + Clear project overview with good context
 + Critical rules prominently displayed
 + Comprehensive coverage of workflows
 Issues Found:
 1. [HIGH] Verbose explanations (lines 45-78)
   Section "Running Tests" has 34 lines that could be 8 lines.
   Impact: Harder to scan, important info buried
 2. [MEDIUM] Duplicate content (lines 102-115, 189-200)
   Same git workflow documented twice.
   Impact: Maintenance burden, inconsistency risk
 3. [MEDIUM] Missing Quick Start section
   No clear "how to get started" instructions.
   Impact: Slower onboarding for Claude
 4. [LOW] Inconsistent header formatting
   Mix of "## Title" and "## Title:" styles.
   Impact: Minor readability issue
 Recommendations:
 1. Add Quick Start section at top (priority: high)
 2. Condense Testing section to essentials (priority: high)
 3. Remove duplicate git workflow (priority: medium)
 4. Standardize header formatting (priority: low)
 Estimated improvement: 15-20 points after changes
 Would you like me to:
 [1] Implement all recommended changes
 [2] Show before/after for specific section
 [3] Generate optimized version for review
 ```
 ## When to Use
 Run `/config-analyze` when:
 - Setting up a new project with existing CLAUDE.md
 - CLAUDE.md feels too long or hard to use
 - Claude seems to miss instructions
 - Before major project changes
 - Periodic maintenance (quarterly)
 ## Follow-Up Actions
 After analysis, you can:
 - Run `/config-optimize` to automatically improve the file
 - Manually address specific issues
 - Request detailed recommendations for any section
 - Compare with best practice templates
 ## Tips
 - Run analysis after significant project changes
 - Address HIGH priority issues first
 - Keep scores above 70/100 for best results
 - Re-analyze after making changes to verify improvement
--- a/plugins/claude-config-maintainer/commands/init.md
+++ b/plugins/claude-config-maintainer/commands/init.md
@@ -0,0 +1,211 @@
 ---
 description: Initialize a new CLAUDE.md file for a project
 ---
 # Initialize CLAUDE.md
 This command creates a new CLAUDE.md file tailored to your project, gathering context and generating appropriate content.
 ## What This Command Does
 1. **Gather Context** - Analyzes project structure and asks clarifying questions
 2. **Detect Stack** - Identifies technologies, frameworks, and tools
 3. **Generate Content** - Creates tailored CLAUDE.md sections
 4. **Review & Refine** - Allows customization before saving
 5. **Save File** - Creates the CLAUDE.md in project root
 ## Usage
 ```
 /config-init
 ```
 Or with options:
 ```
 /config-init --template=api        # Use API project template
 /config-init --minimal             # Create minimal version
 /config-init --comprehensive       # Create detailed version
 ```
 ## Initialization Workflow
 ```
 CLAUDE.md Initialization
 ========================
 Step 1: Project Analysis
 ------------------------
 Scanning project structure...
 Detected:
 - Language: Python 3.11
 - Framework: FastAPI
 - Package Manager: pip (requirements.txt found)
 - Testing: pytest
 - Docker: Yes (Dockerfile found)
 - Git: Yes (.git directory)
 Step 2: Clarifying Questions
 ----------------------------
 1. Project Description:
   What does this project do? (1-2 sentences)
   > [User provides description]
 2. Build/Run Commands:
   Detected commands - are these correct?
   - Install: pip install -r requirements.txt
   - Test: pytest
   - Run: uvicorn main:app --reload
   [Y/n/edit]
 3. Critical Rules:
   Any rules Claude MUST follow?
   Examples: "Never modify migrations", "Always use type hints"
   > [User provides rules]
 4. Sensitive Areas:
   Any files/directories Claude should be careful with?
   > [User provides or skips]
 Step 3: Generate CLAUDE.md
 --------------------------
 Generating content based on:
 - Project type: FastAPI web API
 - Detected technologies
 - Your provided context
 Preview:
 ---
 # CLAUDE.md
 ## Project Overview
 [Generated description]
 ## Quick Start
 ```bash
 pip install -r requirements.txt  # Install dependencies
 pytest                           # Run tests
 uvicorn main:app --reload        # Start dev server
 ```
 ## Architecture
 [Generated based on structure]
 ## Critical Rules
 [Your provided rules]
 ## File Structure
 [Generated from analysis]
 ---
 Save this CLAUDE.md? [Y/n/edit]
 Step 4: Complete
 ----------------
 CLAUDE.md created successfully!
 Location: /path/to/project/CLAUDE.md
 Lines: 87
 Score: 85/100 (following best practices)
 Recommendations:
 - Run /config-analyze periodically to maintain quality
 - Update when adding major features
 - Add troubleshooting section as issues are discovered
 ```
 ## Templates
 ### Minimal Template
 For small projects or when starting fresh:
 - Project Overview (required)
 - Quick Start (required)
 - Critical Rules (required)
 ### Standard Template (default)
 For typical projects:
 - Project Overview
 - Quick Start
 - Architecture
 - Critical Rules
 - Common Operations
 - File Structure
 ### Comprehensive Template
 For large or complex projects:
 - All standard sections plus:
 - Detailed Architecture
 - Troubleshooting
 - Integration Points
 - Development Workflow
 - Deployment Notes
 ## Auto-Detection
 The command automatically detects:
 | What | How |
 |------|-----|
 | Language | File extensions, config files |
 | Framework | package.json, requirements.txt, etc. |
 | Build system | Makefile, package.json scripts, etc. |
 | Testing | pytest.ini, jest.config, etc. |
 | Docker | Dockerfile, docker-compose.yml |
 | Database | Connection strings, ORM configs |
 ## Customization
 After generation, you can:
 - Edit any section before saving
 - Add additional sections
 - Remove unnecessary sections
 - Adjust detail level
 - Add project-specific content
 ## When to Use
 Run `/config-init` when:
 - Starting a new project
 - Project lacks CLAUDE.md
 - Existing CLAUDE.md is outdated/poor quality
 - Taking over an unfamiliar project
 ## Tips
 1. **Provide accurate description** - This shapes the whole file
 2. **Include critical rules** - What must Claude never do?
 3. **Review generated content** - Auto-detection isn't perfect
 4. **Start minimal, grow as needed** - Add sections when required
 5. **Keep it current** - Update when project changes significantly
 ## Examples
 ### For a CLI Tool
 ```
 /config-init
 > Description: CLI tool for managing cloud infrastructure
 > Critical rules: Never delete resources without confirmation, always show dry-run first
 ```
 ### For a Web App
 ```
 /config-init
 > Description: E-commerce platform with React frontend and Node.js backend
 > Critical rules: Never expose API keys, always validate user input, follow the existing component patterns
 ```
 ### For a Library
 ```
 /config-init --template=minimal
 > Description: Python library for parsing log files
 > Critical rules: Maintain backward compatibility, all public functions need docstrings
 ```
--- a/plugins/claude-config-maintainer/commands/optimize.md
+++ b/plugins/claude-config-maintainer/commands/optimize.md
@@ -0,0 +1,178 @@
 ---
 description: Optimize CLAUDE.md structure and content
 ---
 # Optimize CLAUDE.md
 This command automatically optimizes your project's CLAUDE.md file based on best practices and identified issues.
 ## What This Command Does
 1. **Analyze Current File** - Identifies all optimization opportunities
 2. **Plan Changes** - Determines what to restructure, condense, or add
 3. **Show Preview** - Displays before/after comparison
 4. **Apply Changes** - Updates the file with your approval
 5. **Verify Results** - Confirms improvements achieved
 ## Usage
 ```
 /config-optimize
 ```
 Or specify specific optimizations:
 ```
 /config-optimize --condense        # Focus on reducing verbosity
 /config-optimize --restructure     # Focus on reorganization
 /config-optimize --add-missing     # Focus on adding missing sections
 ```
 ## Optimization Actions
 ### Restructure
 - Reorder sections by importance
 - Group related content together
 - Improve header hierarchy
 - Add navigation aids
 ### Condense
 - Remove redundant explanations
 - Convert verbose text to bullet points
 - Eliminate duplicate content
 - Shorten overly detailed sections
 ### Enhance
 - Add missing essential sections
 - Improve unclear instructions
 - Add helpful examples
 - Highlight critical rules
 ### Format
 - Standardize header styles
 - Fix code block formatting
 - Align list formatting
 - Improve table layouts
 ## Expected Output
 ```
 CLAUDE.md Optimization
 ======================
 Current Analysis:
 - Score: 72/100
 - Lines: 245
 - Issues: 4
 Planned Optimizations:
 1. ADD: Quick Start section (new, ~15 lines)
   + Build command
   + Test command
   + Run command
 2. CONDENSE: Testing section (34 → 8 lines)
   Before: Verbose explanation with redundant setup info
   After: Concise command reference with comments
 3. REMOVE: Duplicate git workflow (lines 189-200)
   Keeping: Original at lines 102-115
 4. FORMAT: Standardize headers
   Changing 12 headers from "## Title:" to "## Title"
 Preview Changes? [Y/n] y
 --- CLAUDE.md (before)
 +++ CLAUDE.md (after)
@@ -1,5 +1,20 @@
 # CLAUDE.md
 +## Quick Start
 +
 +```bash
 +# Install dependencies
 +pip install -r requirements.txt
 +
 +# Run tests
 +pytest
 +
 +# Start development server
 +python manage.py runserver
 +```
 +
 ## Project Overview
 ...
 [Full diff shown]
 Apply these changes? [Y/n] y
 Optimization Complete!
 - Previous score: 72/100
 - New score: 89/100
 - Lines reduced: 245 → 198 (-19%)
 - Issues resolved: 4/4
 Backup saved to: .claude/backups/CLAUDE.md.2025-01-18
 ```
 ## Safety Features
 ### Backup Creation
 - Automatic backup before changes
 - Stored in `.claude/backups/`
 - Easy restoration if needed
 ### Preview Mode
 - All changes shown before applying
 - Diff format for easy review
 - Option to approve/reject
 ### Selective Application
 - Can apply individual changes
 - Skip specific optimizations
 - Iterative refinement
 ## Options
 | Option | Description |
 |--------|-------------|
 | `--dry-run` | Show changes without applying |
 | `--no-backup` | Skip backup creation |
 | `--aggressive` | Maximum condensation |
 | `--preserve-comments` | Keep all existing comments |
 | `--section=NAME` | Optimize specific section only |
 ## When to Use
 Run `/config-optimize` when:
 - Analysis shows score below 70
 - File has grown too long
 - Structure needs reorganization
 - Missing critical sections
 - After major refactoring
 ## Best Practices
 1. **Run analysis first** - Understand current state
 2. **Review preview carefully** - Ensure nothing important lost
 3. **Test after changes** - Verify Claude follows instructions
 4. **Keep backups** - Restore if issues arise
 5. **Iterate** - Multiple small optimizations beat one large one
 ## Rollback
 If optimization causes issues:
 ```bash
 # Restore from backup
 cp .claude/backups/CLAUDE.md.TIMESTAMP ./CLAUDE.md
 ```
 Or ask:
 ```
 Restore CLAUDE.md from the most recent backup
 ```
--- a/plugins/projman/.claude-plugin/plugin.json
+++ b/plugins/projman/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
  "name": "projman",
-  "version": "0.1.0",
+  "version": "2.0.0",
-  "description": "Sprint planning and project management with Gitea and Wiki.js integration",
+  "description": "Sprint planning and project management with Gitea integration",
  "author": {
    "name": "Bandit Labs",
    "email": "dev@banditlabs.io"
@@ -12,7 +12,7 @@
    "project-management",
    "sprint-planning",
    "gitea",
-    "wikijs",
+    "agile",
-    "agile"
+    "lessons-learned"
  ]
 }
--- a/plugins/projman/.mcp.json
+++ b/plugins/projman/.mcp.json
@@ -7,14 +7,6 @@
      "env": {
        "PYTHONPATH": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/gitea"
      }
    },
    "wikijs": {
      "command": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/wikijs/.venv/bin/python",
      "args": ["-m", "mcp_server.server"],
      "cwd": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/wikijs",
      "env": {
        "PYTHONPATH": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/wikijs"
      }
    }
  }
 }
--- a/plugins/projman/CONFIGURATION.md
+++ b/plugins/projman/CONFIGURATION.md
@@ -1,18 +1,18 @@
-# Configuration Guide - Projman Plugin
+# Configuration Guide - Projman Plugin v2.0.0
 Complete setup and configuration instructions for the Projman project management plugin.
 ## Overview
 The Projman plugin uses a **hybrid configuration** approach:
- **System-level:** Credentials for Gitea and Wiki.js (stored once per machine)
+- **System-level:** Credentials for Gitea (stored once per machine)
- **Project-level:** Repository and project paths (stored per project)
+- **Project-level:** Repository path (stored per project)
 This design allows:
- ✅ Single token per service (update once, use everywhere)
+- Single token per service (update once, use everywhere)
- ✅ Easy multi-project setup (just add `.env` per project)
+- Easy multi-project setup (just add `.env` per project)
- ✅ Security (tokens never committed to git)
+- Security (tokens never committed to git)
- ✅ Project isolation (each project has its own scope)
+- Project isolation (each project has its own scope)
 ## Prerequisites
@@ -20,7 +20,7 @@ Before configuring the plugin, ensure you have:
 1. **Python 3.10+** installed
   ```bash
-   python --version  # Should be 3.10.0 or higher
+   python3 --version  # Should be 3.10.0 or higher
   ```
 2. **Git repository** initialized
@@ -32,26 +32,20 @@ Before configuring the plugin, ensure you have:
   - Create issues
   - Manage labels
   - Read organization information
   - Access repository wiki
-4. **Wiki.js access** with an account and permissions to:
+4. **Claude Code** installed and working
   - Create and edit pages
   - Manage tags
   - Read and write content
-5. **Claude Code** installed and working
+## Step 1: Install MCP Server
-## Step 1: Install MCP Servers
+The plugin bundles the Gitea MCP server at `mcp-servers/gitea/`:
 The plugin requires two MCP servers installed at `../mcp-servers/` relative to the plugin:
 ### 1.1 Install Gitea MCP Server
 ```bash
-# Navigate to Gitea MCP server directory
+# Navigate to MCP server directory (inside plugin)
-cd ../mcp-servers/gitea
+cd plugins/projman/mcp-servers/gitea
 # Create virtual environment
-python -m venv .venv
+python3 -m venv .venv
 # Activate virtual environment
 source .venv/bin/activate  # Linux/Mac
@@ -63,32 +57,12 @@ pip install -r requirements.txt
 # Verify installation
 python -c "from mcp_server import server; print('Gitea MCP Server installed successfully')"
 # Deactivate when done
 deactivate
 ```
-### 1.2 Install Wiki.js MCP Server
+## Step 2: Generate Gitea API Token
 ```bash
 # Navigate to Wiki.js MCP server directory
 cd ../mcp-servers/wikijs
 # Create virtual environment
 python -m venv .venv
 # Activate virtual environment
 source .venv/bin/activate  # Linux/Mac
 # or
 .venv\Scripts\activate     # Windows
 # Install dependencies
 pip install -r requirements.txt
 # Verify installation
 python -c "from mcp_server import server; print('Wiki.js MCP Server installed successfully')"
 ```
 ## Step 2: Generate API Tokens
 ### 2.1 Generate Gitea API Token
 1. Log into Gitea: https://gitea.example.com
 2. Navigate to: **User Icon** (top right) → **Settings**
@@ -98,41 +72,23 @@ python -c "from mcp_server import server; print('Wiki.js MCP Server installed su
 6. Configure token:
   - **Token Name:** `claude-code-projman`
   - **Permissions:**
-     - ✅ `repo` (all sub-permissions) - Repository access
+     - `repo` (all sub-permissions) - Repository access
-     - ✅ `read:org` - Read organization information and labels
+     - `read:org` - Read organization information and labels
-     - ✅ `read:user` - Read user information
+     - `read:user` - Read user information
     - `write:repo` - Wiki access
 7. Click **Generate Token**
 8. **IMPORTANT:** Copy token immediately (shown only once!)
 9. Save token securely - you'll need it in Step 3
 **Token Permissions Explained:**
- `repo` - Create, read, update issues and labels
+- `repo` - Create, read, update issues, labels, and wiki
 - `read:org` - Access organization-level labels
 - `read:user` - Associate issues with user account
-
+- `write:repo` - Create wiki pages for lessons learned
 ### 2.2 Generate Wiki.js API Token
 1. Log into Wiki.js: https://wiki.your-company.com
 2. Navigate to: **Administration** (top right)
 3. Click **API Access** in the left sidebar
 4. Click **New API Key**
 5. Configure API key:
   - **Name:** `claude-code-projman`
   - **Expiration:** None (or set to your security policy)
   - **Permissions:**
     - ✅ **Pages:** Read, Create, Update
     - ✅ **Search:** Read
 6. Click **Create**
 7. **IMPORTANT:** Copy the JWT token immediately (shown only once!)
 8. Save token securely - you'll need it in Step 3
 **Token Permissions Explained:**
 - Pages (read/create/update) - Manage documentation and lessons learned
 - Search (read) - Find relevant lessons from previous sprints
 ## Step 3: System-Level Configuration
-Create system-wide configuration files in `~/.config/claude/`:
+Create system-wide configuration file in `~/.config/claude/`:
 ### 3.1 Create Configuration Directory
@@ -145,55 +101,35 @@ mkdir -p ~/.config/claude
 ```bash
 cat > ~/.config/claude/gitea.env << 'EOF'
 # Gitea API Configuration
-GITEA_API_URL=https://gitea.example.com/api/v1
+GITEA_URL=https://gitea.example.com
-GITEA_API_TOKEN=your_gitea_token_here
+GITEA_TOKEN=your_gitea_token_here
-GITEA_OWNER=bandit
+GITEA_ORG=your_organization
 EOF
 # Secure the file (owner read/write only)
 chmod 600 ~/.config/claude/gitea.env
 ```
-**Replace `your_gitea_token_here` with the token from Step 2.1**
+**Replace placeholders:**
 - `your_gitea_token_here` with the token from Step 2
 - `your_organization` with your Gitea organization name
 **Configuration Variables:**
- `GITEA_API_URL` - Gitea API endpoint (includes `/api/v1`)
+- `GITEA_URL` - Gitea base URL (without `/api/v1`)
- `GITEA_API_TOKEN` - Personal access token from Step 2.1
+- `GITEA_TOKEN` - Personal access token from Step 2
- `GITEA_OWNER` - Organization or user name (e.g., `bandit`)
+- `GITEA_ORG` - Organization name (e.g., `bandit`)
-### 3.3 Configure Wiki.js
+### 3.3 Verify System Configuration
 ```bash
-cat > ~/.config/claude/wikijs.env << 'EOF'
+# Check file exists and has correct permissions
-# Wiki.js API Configuration
+ls -la ~/.config/claude/gitea.env
 WIKIJS_API_URL=https://wiki.your-company.com/graphql
 WIKIJS_API_TOKEN=your_wikijs_token_here
 WIKIJS_BASE_PATH=/your-org
 EOF
 # Secure the file (owner read/write only)
 chmod 600 ~/.config/claude/wikijs.env
 ```
 **Replace `your_wikijs_token_here` with the JWT token from Step 2.2**
 **Configuration Variables:**
 - `WIKIJS_API_URL` - Wiki.js GraphQL endpoint (includes `/graphql`)
 - `WIKIJS_API_TOKEN` - API key from Step 2.2 (JWT format)
 - `WIKIJS_BASE_PATH` - Base path in Wiki.js (e.g., `/your-org`)
 ### 3.4 Verify System Configuration
 ```bash
 # Check files exist and have correct permissions
 ls -la ~/.config/claude/
 # Should show:
 # -rw------- gitea.env
 # -rw------- wikijs.env
 ```
-**Security Note:** Files should have `600` permissions (owner read/write only) to protect API tokens.
+**Security Note:** File should have `600` permissions (owner read/write only) to protect API tokens.
 ## Step 4: Project-Level Configuration
@@ -206,42 +142,28 @@ For each project where you'll use Projman, create a `.env` file:
 cat > .env << 'EOF'
 # Gitea Repository Configuration
 GITEA_REPO=your-repo-name
 # Wiki.js Project Configuration
 WIKIJS_PROJECT=projects/your-project-name
 EOF
 ```
-**Example for CuisineFlow project:**
+**Example for MyProject:**
 ```bash
 cat > .env << 'EOF'
-GITEA_REPO=cuisineflow
+GITEA_REPO=my-project
 WIKIJS_PROJECT=projects/cuisineflow
 EOF
 ```
-### 4.2 Add .env to .gitignore
+### 4.2 Verify Project Configuration
 **CRITICAL:** Never commit `.env` to git!
 ```bash
 # Add to .gitignore
 echo ".env" >> .gitignore
 # Verify
 git check-ignore .env  # Should output: .env
 ```
 ### 4.3 Verify Project Configuration
 ```bash
 # Check .env exists
 ls -la .env
-# Check it's in .gitignore
+# Check .env content
-cat .gitignore | grep "\.env"
+cat .env
 ```
 **Note:** The `.env` file may already be in your `.gitignore`. If your project uses `.env` for other purposes, the Gitea configuration will merge with existing variables.
 ## Step 5: Configuration Verification
 Test that everything is configured correctly:
@@ -256,23 +178,21 @@ curl -H "Authorization: token YOUR_GITEA_TOKEN" \
 # Should return your user information in JSON format
 ```
-### 5.2 Test Wiki.js Connection
+### 5.2 Test Wiki Access
 ```bash
-# Test GraphQL endpoint
+# Test wiki API
-curl -H "Authorization: Bearer YOUR_WIKIJS_TOKEN" \
+curl -H "Authorization: token YOUR_GITEA_TOKEN" \
-  -H "Content-Type: application/json" \
+  https://gitea.example.com/api/v1/repos/YOUR_ORG/YOUR_REPO/wiki/pages
  -d '{"query": "{ pages { list { id title } } }"}' \
  https://wiki.your-company.com/graphql
-# Should return pages data in JSON format
+# Should return list of wiki pages (or empty array)
 ```
 ### 5.3 Test MCP Server Loading
 ```bash
 # Navigate to plugin directory
-cd projman
+cd plugins/projman
 # Verify .mcp.json exists
 cat .mcp.json
@@ -283,9 +203,19 @@ claude --debug
 ## Step 6: Initialize Plugin
-### 6.1 Sync Label Taxonomy
+### 6.1 Run Initial Setup
-First time setup - fetch labels from Gitea:
+```bash
 /initial-setup
 ```
 This will:
 - Validate Gitea MCP server connection
 - Test credential configuration
 - Sync label taxonomy
 - Verify required directory structure
 ### 6.2 Sync Label Taxonomy
 ```bash
 /labels-sync
@@ -296,15 +226,16 @@ This will:
 - Update `skills/label-taxonomy/labels-reference.md`
 - Enable intelligent label suggestions
-### 6.2 Verify Commands Available
+### 6.3 Verify Commands Available
 ```bash
 # List available commands
-/sprint-plan --help
+/sprint-plan
-/sprint-start --help
+/sprint-start
-/sprint-status --help
+/sprint-status
-/sprint-close --help
+/sprint-close
-/labels-sync --help
+/labels-sync
 /initial-setup
 ```
 ## Configuration Files Reference
@@ -313,16 +244,9 @@ This will:
 **`~/.config/claude/gitea.env`:**
 ```bash
-GITEA_API_URL=https://gitea.example.com/api/v1
+GITEA_URL=https://gitea.example.com
-GITEA_API_TOKEN=glpat-xxxxxxxxxxxxxxxxxxxxx
+GITEA_TOKEN=glpat-xxxxxxxxxxxxxxxxxxxxx
-GITEA_OWNER=bandit
+GITEA_ORG=your_organization
 ```
 **`~/.config/claude/wikijs.env`:**
 ```bash
 WIKIJS_API_URL=https://wiki.your-company.com/graphql
 WIKIJS_API_TOKEN=eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9...
 WIKIJS_BASE_PATH=/your-org
 ```
 ### Project-Level Files
@@ -330,12 +254,6 @@ WIKIJS_BASE_PATH=/your-org
 **`.env` (in project root):**
 ```bash
 GITEA_REPO=your-repo-name
 WIKIJS_PROJECT=projects/your-project-name
 ```
 **`.gitignore` (must include):**
 ```
 .env
 ```
 ### Plugin Configuration
@@ -345,19 +263,11 @@ WIKIJS_PROJECT=projects/your-project-name
 {
  "mcpServers": {
    "gitea": {
-      "command": "python",
+      "command": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/gitea/.venv/bin/python",
      "args": ["-m", "mcp_server.server"],
-      "cwd": "${CLAUDE_PLUGIN_ROOT}/../mcp-servers/gitea",
+      "cwd": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/gitea",
      "env": {
-        "PYTHONPATH": "${CLAUDE_PLUGIN_ROOT}/../mcp-servers/gitea"
+        "PYTHONPATH": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/gitea"
      }
    },
    "wikijs": {
      "command": "python",
      "args": ["-m", "mcp_server.server"],
      "cwd": "${CLAUDE_PLUGIN_ROOT}/../mcp-servers/wikijs",
      "env": {
        "PYTHONPATH": "${CLAUDE_PLUGIN_ROOT}/../mcp-servers/wikijs"
      }
    }
  }
@@ -375,24 +285,21 @@ To use Projman with multiple projects:
 ```bash
 # ~/projects/my-app/.env
 GITEA_REPO=my-app
 WIKIJS_PROJECT=projects/my-app
 ```
 **Project 2: App Site**
 ```bash
 # ~/projects/my-app-site/.env
 GITEA_REPO=my-app-site
 WIKIJS_PROJECT=projects/my-app-site
 ```
 **Project 3: Company Site**
 ```bash
 # ~/projects/company-site/.env
 GITEA_REPO=company-site
 WIKIJS_PROJECT=projects/company-site
 ```
-Each project operates independently with its own issues and lessons learned.
+Each project operates independently with its own issues and lessons learned (stored in each repository's wiki).
 ## Troubleshooting
@@ -404,7 +311,6 @@ Each project operates independently with its own issues and lessons learned.
 ```bash
 # Check system config exists
 ls -la ~/.config/claude/gitea.env
 ls -la ~/.config/claude/wikijs.env
 # If missing, recreate from Step 3
 ```
@@ -419,10 +325,6 @@ ls -la ~/.config/claude/wikijs.env
 curl -H "Authorization: token YOUR_TOKEN" \
  https://gitea.example.com/api/v1/user
 # Test Wiki.js token
 curl -H "Authorization: Bearer YOUR_TOKEN" \
  https://wiki.your-company.com/graphql
 # If fails, regenerate token (Step 2)
 ```
@@ -433,13 +335,12 @@ curl -H "Authorization: Bearer YOUR_TOKEN" \
 **Solution:**
 ```bash
 # Check Python virtual environment exists
-ls ../mcp-servers/gitea/.venv
+ls plugins/projman/mcp-servers/gitea/.venv
 ls ../mcp-servers/wikijs/.venv
 # If missing, reinstall (Step 1)
 # Check dependencies installed
-cd ../mcp-servers/gitea
+cd plugins/projman/mcp-servers/gitea
 source .venv/bin/activate
 python -c "import requests; import mcp"
@@ -447,35 +348,41 @@ python -c "import requests; import mcp"
 pip install -r requirements.txt
 ```
-### Wrong repository or project
+### Wrong repository
-**Problem:** Issues created in wrong repo or lessons saved to wrong project
+**Problem:** Issues created in wrong repo
 **Solution:**
 ```bash
 # Check project .env configuration
 cat .env
-# Verify GITEA_REPO matches Gitea repository name
+# Verify GITEA_REPO matches Gitea repository name exactly
 # Verify WIKIJS_PROJECT matches Wiki.js project path
 # Update if incorrect
 nano .env
 ```
 ### Permissions errors
-**Problem:** "Permission denied" when creating issues or pages
+**Problem:** "Permission denied" when creating issues or wiki pages
 **Solution:**
- **Gitea:** Verify token has `repo` and `read:org` permissions (Step 2.1)
+- Verify token has `repo`, `read:org`, and `write:repo` permissions (Step 2)
- **Wiki.js:** Verify token has Pages (create/update) permissions (Step 2.2)
+- Regenerate token with correct permissions if needed
- Regenerate tokens with correct permissions if needed
+
 ### Repository not in organization
 **Problem:** "Repository must belong to configured organization"
 **Solution:**
 - Verify `GITEA_ORG` in system config matches the organization owning the repository
 - Verify `GITEA_REPO` belongs to that organization
 - Fork the repository to your organization if needed
 ## Security Best Practices
 1. **Never commit tokens**
-   - Keep `.env` in `.gitignore`
+   - Keep credentials in `~/.config/claude/` only
   - Never hardcode tokens in code
   - Use system-level config for credentials
@@ -491,51 +398,43 @@ nano .env
 4. **Minimum permissions**
   - Only grant required permissions
-   - Gitea: `repo`, `read:org`, `read:user`
+   - Gitea: `repo`, `read:org`, `read:user`, `write:repo`
   - Wiki.js: Pages (read/create/update), Search (read)
 5. **Monitor usage**
   - Review Gitea access logs periodically
   - Check Wiki.js audit logs
   - Watch for unexpected API usage
 ## Next Steps
 After configuration is complete:
-1. ✅ Run `/labels-sync` to fetch label taxonomy
+1. Run `/initial-setup` to verify everything works
-2. ✅ Try `/sprint-plan` to start your first sprint
+2. Run `/labels-sync` to fetch label taxonomy
-3. ✅ Read [README.md](./README.md) for usage guide
+3. Try `/sprint-plan` to start your first sprint
-4. ✅ Review command documentation in `commands/`
+4. Read [README.md](./README.md) for usage guide
 ## Support
 **Configuration Issues:**
 - Check [README.md](./README.md) troubleshooting section
 - Review MCP server documentation:
  - [Gitea MCP](../mcp-servers/gitea/README.md)
  - [Wiki.js MCP](../mcp-servers/wikijs/README.md)
 - Contact repository maintainer for support
 **Questions:**
 - Read command documentation: `commands/*.md`
- Check agent descriptions in `agents/` (Phase 3)
+- Check agent descriptions in `agents/`
 - Review skills: `skills/label-taxonomy/`
 ---
 **Configuration Status Checklist:**
 - [ ] Python 3.10+ installed
- [ ] Gitea MCP server installed
+- [ ] Gitea MCP server installed (in `mcp-servers/gitea/`)
- [ ] Wiki.js MCP server installed
+- [ ] Gitea API token generated with correct permissions
- [ ] Gitea API token generated
+- [ ] System config created (`~/.config/claude/gitea.env`)
 - [ ] Wiki.js API token generated
 - [ ] System config created (`~/.config/claude/*.env`)
 - [ ] Project config created (`.env`)
 - [ ] `.env` added to `.gitignore`
 - [ ] Gitea connection tested
- [ ] Wiki.js connection tested
+- [ ] Wiki access tested
 - [ ] `/initial-setup` completed successfully
 - [ ] `/labels-sync` completed successfully
 - [ ] Commands verified available
--- a/plugins/projman/README.md
+++ b/plugins/projman/README.md
@@ -1,18 +1,20 @@
-# Projman - Project Management for Claude Code
+# Projman v2.0.0 - Project Management for Claude Code
-Sprint planning and project management plugin with Gitea and Wiki.js integration.
+Sprint planning and project management plugin with full Gitea integration.
 ## Overview
-Projman transforms a proven 15-sprint workflow into a distributable Claude Code plugin. It provides AI-guided sprint planning, intelligent issue creation with label taxonomy, and systematic lessons learned capture to prevent repeated mistakes.
+Projman transforms a proven 15-sprint workflow into a distributable Claude Code plugin. It provides AI-guided sprint planning, intelligent issue creation with label taxonomy, native issue dependencies, parallel task execution, and systematic lessons learned capture via Gitea Wiki.
 **Key Features:**
- 🎯 **Sprint Planning** - AI-guided architecture analysis and issue creation
+- **Sprint Planning** - AI-guided architecture analysis and issue creation
- 🏷️ **Smart Label Suggestions** - Intelligent label recommendations from 44-label taxonomy
+- **Smart Label Suggestions** - Intelligent label recommendations from 43-label taxonomy
- 📚 **Lessons Learned** - Systematic capture and search of sprint insights
+- **Issue Dependencies** - Native Gitea dependencies with parallel execution batching
- 🔒 **Branch-Aware Security** - Prevents accidental changes on production branches
+- **Milestones** - Sprint milestone management and tracking
- ⚙️ **Hybrid Configuration** - Simple setup with system + project-level config
+- **Lessons Learned** - Systematic capture and search via Gitea Wiki
- 🤖 **Three-Agent Model** - Planner, Orchestrator, and Executor agents
+- **Branch-Aware Security** - Prevents accidental changes on production branches
 - **Three-Agent Model** - Planner, Orchestrator, and Executor agents
 - **CLI Tools Blocked** - All operations via MCP tools only (no `tea` or `gh`)
 ## Quick Start
@@ -20,52 +22,38 @@ Projman transforms a proven 15-sprint workflow into a distributable Claude Code
 - Claude Code installed
 - Access to Gitea instance with API token
 - Access to Wiki.js instance with API token
 - Python 3.10+ installed
 - Git repository initialized
-### 2. Install MCP Servers
+### 2. Install MCP Server
-The plugin requires two shared MCP servers:
+The plugin bundles the Gitea MCP server:
 ```bash
-# Navigate to MCP servers directory
+cd plugins/projman/mcp-servers/gitea
-cd ../mcp-servers/gitea
+python3 -m venv .venv
 python -m venv .venv
 source .venv/bin/activate  # or .venv\Scripts\activate on Windows
 pip install -r requirements.txt
 cd ../wikijs
 python -m venv .venv
 source .venv/bin/activate
 pip install -r requirements.txt
 ```
 See [CONFIGURATION.md](./CONFIGURATION.md) for detailed setup instructions.
 ### 3. Configure System-Level Settings
-Create system-wide configuration with your Gitea and Wiki.js credentials:
+Create system-wide configuration with your Gitea credentials:
 ```bash
 mkdir -p ~/.config/claude
 # Gitea configuration
-cat > ~/.config/claude/gitea.env << EOF
+cat > ~/.config/claude/gitea.env << 'EOF'
-GITEA_API_URL=https://gitea.example.com/api/v1
+GITEA_URL=https://gitea.example.com
-GITEA_API_TOKEN=your_gitea_token_here
+GITEA_TOKEN=your_gitea_token_here
-GITEA_OWNER=bandit
+GITEA_ORG=your_organization
 EOF
-# Wiki.js configuration
+# Secure the file
-cat > ~/.config/claude/wikijs.env << EOF
+chmod 600 ~/.config/claude/gitea.env
 WIKIJS_API_URL=https://wiki.your-company.com/graphql
 WIKIJS_API_TOKEN=your_wikijs_token_here
 WIKIJS_BASE_PATH=/your-org
 EOF
 # Secure the files
 chmod 600 ~/.config/claude/*.env
 ```
 ### 4. Configure Project-Level Settings
@@ -74,21 +62,15 @@ In your project root directory, create a `.env` file:
 ```bash
 # In your project directory
-cat > .env << EOF
+cat > .env << 'EOF'
 GITEA_REPO=your-repo-name
 WIKIJS_PROJECT=projects/your-project-name
 EOF
 # Add to .gitignore
 echo ".env" >> .gitignore
 ```
-### 5. Sync Label Taxonomy
+### 5. Run Initial Setup
 Fetch the label taxonomy from Gitea:
 ```bash
-/labels-sync
+/initial-setup
 ```
 ### 6. Start Planning!
@@ -103,54 +85,54 @@ Fetch the label taxonomy from Gitea:
 Start sprint planning with the AI planner agent.
 **What it does:**
 - Validates repository organization and label taxonomy
 - Asks clarifying questions about sprint goals
 - Searches relevant lessons learned from previous sprints
 - Performs architecture analysis
 - Creates Gitea issues with intelligent label suggestions
- Generates planning document
+- Sets up issue dependencies for parallel execution
 - Creates sprint milestone
 **Pre-Planning Validations:**
 1. Repository belongs to configured organization
 2. Required label categories exist
 3. `docs/changes/` folder exists in repository
 **Task Naming:** `[Sprint XX] <type>: <description>`
 **When to use:** Beginning of a new sprint or when planning a major feature
 **Example:**
 ```
 /sprint-plan
 > "I want to plan a sprint for user authentication"
 ```
 ### `/sprint-start`
 Begin sprint execution with the orchestrator agent.
 **What it does:**
- Reviews open sprint issues
+- Reviews open sprint issues and dependencies
- Searches relevant lessons learned by tags
+- Batches tasks by dependency graph for parallel execution
 - Identifies next task based on priority and dependencies
 - Generates lean execution prompts
 - Tracks progress
-**When to use:** After planning, when ready to start implementation
+**Parallel Execution:**
 ```
 Batch 1 (parallel): Task A, Task B, Task C
 Batch 2 (parallel): Task D, Task E  (depend on Batch 1)
 Batch 3 (sequential): Task F        (depends on Batch 2)
 ```
-**Example:**
+**Branch Naming:** `feat/123-task-title`, `fix/456-bug-fix`, `debug/789-investigation`
-```
+
-/sprint-start
+**When to use:** After planning, when ready to start implementation
 ```
 ### `/sprint-status`
 Check current sprint progress.
 **What it does:**
 - Lists all sprint issues by status (open, in progress, blocked, completed)
- Identifies blockers and priorities
+- Shows dependency analysis and blocked tasks
- Shows completion percentage
+- Displays completion percentage
- Highlights critical items needing attention
+- Shows milestone progress
 **When to use:** Daily standup, progress check, deciding what to work on next
 **Example:**
 ```
 /sprint-status
 ```
 ### `/sprint-close`
 Complete sprint and capture lessons learned.
@@ -158,38 +140,39 @@ Complete sprint and capture lessons learned.
 - Reviews sprint completion
 - Captures lessons learned (what went wrong, what went right)
 - Tags lessons for discoverability
- Saves lessons to Wiki.js
+- Saves lessons to Gitea Wiki
 - Closes sprint milestone
 - Handles git operations (merge, tag, cleanup)
 **When to use:** End of sprint, before starting the next one
 **Example:**
 ```
 /sprint-close
 ```
 **CRITICAL:** Don't skip this! After 15 sprints without lesson capture, teams repeat the same mistakes.
 ### `/labels-sync`
 Synchronize label taxonomy from Gitea.
 **What it does:**
 - Validates repository belongs to organization
 - Fetches current labels from Gitea (org + repo)
 - Validates required label categories
 - Compares with local reference
 - Detects changes (new, modified, removed labels)
 - Updates local taxonomy reference
 - Updates suggestion logic
 **When to use:**
 - First-time setup
 - Monthly maintenance
 - When new labels are added to Gitea
 - When label suggestions seem incorrect
-**Example:**
+### `/initial-setup`
-```
+Run initial setup for a new project.
-/labels-sync
+
-```
+**What it does:**
 - Validates Gitea MCP server connection
 - Tests credential configuration
 - Syncs label taxonomy
 - Creates required directory structure
 **When to use:** First time setting up projman for a project
 ## Agents
@@ -197,10 +180,12 @@ Synchronize label taxonomy from Gitea.
 **Personality:** Thoughtful, methodical, asks clarifying questions
 **Responsibilities:**
 - Pre-planning validations (org, labels, folder structure)
 - Sprint planning and architecture analysis
 - Asking clarifying questions before making assumptions
- Searching relevant lessons learned
+- Searching relevant lessons learned via Gitea Wiki
 - Creating well-structured Gitea issues
 - Setting up issue dependencies
 - Suggesting appropriate labels based on context
 **Invoked by:** `/sprint-plan`
@@ -209,11 +194,11 @@ Synchronize label taxonomy from Gitea.
 **Personality:** Concise, action-oriented, detail-focused
 **Responsibilities:**
- Coordinating sprint execution
+- Coordinating sprint execution with parallel batching
 - Generating lean execution prompts (not full documents)
 - Tracking progress meticulously
 - Managing Git operations
- Handling task dependencies
+- Handling task dependencies via `get_execution_order`
 - Capturing lessons learned at sprint close
 **Invoked by:** `/sprint-start`, `/sprint-close`
@@ -225,14 +210,72 @@ Synchronize label taxonomy from Gitea.
 - Providing implementation guidance
 - Writing clean, tested code
 - Following architectural decisions from planning
- Generating completion reports
+- Creating branches with proper naming (`feat/`, `fix/`, `debug/`)
 - Generating MR body template
 - Code review and quality standards
-**Usage:** Can be invoked by the orchestrator when implementation guidance is needed.
+**MR Body Template:**
 ```markdown
 ## Summary
 <1-3 bullet points>
 ## Test plan
 <Testing approach>
 Closes #<issue-number>
 ```
 ## MCP Tools
 ### Issue Tools
 | Tool | Description |
 |------|-------------|
 | `list_issues` | Query issues with filters |
 | `get_issue` | Fetch single issue details |
 | `create_issue` | Create new issue with labels |
 | `update_issue` | Modify existing issue |
 | `add_comment` | Add comments to issues |
 ### Label Tools
 | Tool | Description |
 |------|-------------|
 | `get_labels` | Fetch org + repo label taxonomy |
 | `suggest_labels` | Analyze context and suggest appropriate labels |
 | `create_label` | Create missing required labels |
 ### Milestone Tools
 | Tool | Description |
 |------|-------------|
 | `list_milestones` | List sprint milestones |
 | `get_milestone` | Get milestone details |
 | `create_milestone` | Create sprint milestone |
 | `update_milestone` | Update/close milestone |
 ### Dependency Tools
 | Tool | Description |
 |------|-------------|
 | `list_issue_dependencies` | Get issue dependencies |
 | `create_issue_dependency` | Create dependency between issues |
 | `get_execution_order` | Get parallel execution batches |
 ### Wiki Tools (Gitea Wiki)
 | Tool | Description |
 |------|-------------|
 | `list_wiki_pages` | List wiki pages |
 | `get_wiki_page` | Fetch specific page content |
 | `create_wiki_page` | Create new wiki page |
 | `create_lesson` | Create lessons learned document |
 | `search_lessons` | Search past lessons by tags |
 ### Validation Tools
 | Tool | Description |
 |------|-------------|
 | `validate_repo_org` | Check repo belongs to organization |
 | `get_branch_protection` | Check branch protection rules |
 ## Label Taxonomy
-The plugin uses a dynamic 44-label taxonomy (28 organization + 16 repository):
+The plugin uses a dynamic 43-label taxonomy (27 organization + 16 repository):
 **Organization Labels:**
 - Agent/* (2): Human, Claude
@@ -254,20 +297,19 @@ Labels are fetched dynamically from Gitea using `/labels-sync`.
 The plugin implements defense-in-depth branch detection to prevent accidental changes on production:
 **Development Branches** (`development`, `develop`, `feat/*`, `dev/*`):
- ✅ Full planning and execution capabilities
+- Full planning and execution capabilities
- ✅ Can create and modify issues
+- Can create and modify issues
- ✅ Can capture lessons learned
+- Can capture lessons learned
 **Staging Branches** (`staging`, `stage/*`):
- ✅ Can create issues to document bugs
+- Can create issues to document bugs
- ❌ Cannot modify code
+- Cannot modify code
- ⚠️ Warns when attempting changes
+- Warns when attempting changes
 **Production Branches** (`main`, `master`, `prod/*`):
- ✅ Read-only access
+- Read-only access
- ❌ Cannot create issues
+- Cannot create issues
- ❌ Cannot modify code
+- Blocks all planning and execution
 - 🛑 Blocks all planning and execution
 ## Lessons Learned System
@@ -279,8 +321,8 @@ The plugin implements defense-in-depth branch detection to prevent accidental ch
 **Solution:** Mandatory lessons learned capture at sprint close, searchable at sprint start.
 **Workflow:**
-1. **Sprint Close:** Orchestrator captures lessons (what went wrong, what went right, preventable mistakes)
+1. **Sprint Close:** Orchestrator captures lessons via Gitea Wiki tools
-2. **Wiki.js Storage:** Lessons saved to `/projects/{project}/lessons-learned/sprints/`
+2. **Gitea Wiki Storage:** Lessons saved to repository wiki under `lessons-learned/sprints/`
 3. **Sprint Start:** Planner searches relevant lessons by tags and keywords
 4. **Prevention:** Apply learned insights to avoid repeating mistakes
@@ -304,19 +346,57 @@ The plugin implements defense-in-depth branch detection to prevent accidental ch
 [technology, component, type]
 ```
 ## Architecture
 ```
 projman/
 ├── .claude-plugin/
 │   └── plugin.json          # Plugin manifest
 ├── .mcp.json                # MCP server configuration
 ├── mcp-servers/             # Bundled MCP server
 │   └── gitea/
 │       ├── .venv/
 │       ├── requirements.txt
 │       ├── mcp_server/
 │       │   ├── server.py
 │       │   ├── gitea_client.py
 │       │   └── tools/
 │       │       ├── issues.py
 │       │       ├── labels.py
 │       │       ├── wiki.py
 │       │       ├── milestones.py
 │       │       └── dependencies.py
 │       └── tests/
 ├── commands/                # Slash commands
 │   ├── sprint-plan.md
 │   ├── sprint-start.md
 │   ├── sprint-status.md
 │   ├── sprint-close.md
 │   ├── labels-sync.md
 │   └── initial-setup.md
 ├── agents/                  # Agent prompts
 │   ├── planner.md
 │   ├── orchestrator.md
 │   └── executor.md
 ├── skills/                  # Supporting knowledge
 │   └── label-taxonomy/
 │       └── labels-reference.md
 ├── README.md                # This file
 └── CONFIGURATION.md         # Setup guide
 ```
 ## Configuration
 See [CONFIGURATION.md](./CONFIGURATION.md) for detailed configuration instructions.
 **Quick summary:**
- **System-level:** `~/.config/claude/gitea.env` and `wikijs.env` (credentials)
+- **System-level:** `~/.config/claude/gitea.env` (credentials)
- **Project-level:** `.env` in project root (repository and project paths)
+- **Project-level:** `.env` in project root (repository specification)
 - **MCP Servers:** Located at `../mcp-servers/` (shared by multiple plugins)
 ## Troubleshooting
 ### Plugin not loading
- Check that MCP servers are installed: `ls ../mcp-servers/gitea/.venv`
+- Check that MCP server is installed: `ls mcp-servers/gitea/.venv`
 - Verify plugin manifest: `cat .claude-plugin/plugin.json | jq`
 - Check Claude Code logs for errors
@@ -325,11 +405,6 @@ See [CONFIGURATION.md](./CONFIGURATION.md) for detailed configuration instructio
 - Test token: `curl -H "Authorization: token YOUR_TOKEN" https://gitea.example.com/api/v1/user`
 - Check network connectivity
 ### Cannot connect to Wiki.js
 - Verify `~/.config/claude/wikijs.env` exists and has correct URL and token
 - Check Wiki.js GraphQL endpoint: `https://wiki.your-company.com/graphql`
 - Verify API token has pages read/write permissions
 ### Labels not syncing
 - Run `/labels-sync` manually
 - Check Gitea API token has `read:org` and `repo` permissions
@@ -340,100 +415,28 @@ See [CONFIGURATION.md](./CONFIGURATION.md) for detailed configuration instructio
 - Check current branch: `git branch --show-current`
 - If on wrong branch, switch: `git checkout development`
 ## Architecture
 ```
 projman/
 ├── .claude-plugin/
 │   └── plugin.json          # Plugin manifest
 ├── .mcp.json                # MCP server configuration
 ├── commands/                # Slash commands
 │   ├── sprint-plan.md
 │   ├── sprint-start.md
 │   ├── sprint-status.md
 │   ├── sprint-close.md
 │   └── labels-sync.md
 ├── agents/                  # Agent prompts (Phase 3)
 │   ├── planner.md
 │   ├── orchestrator.md
 │   └── executor.md
 ├── skills/                  # Supporting knowledge
 │   └── label-taxonomy/
 │       └── labels-reference.md
 ├── README.md                # This file
 └── CONFIGURATION.md         # Setup guide
 ```
 **MCP Servers (shared):**
 ```
 ../mcp-servers/
 ├── gitea/                   # Gitea MCP server
 │   ├── .venv/
 │   ├── mcp_server/
 │   └── tests/
 └── wikijs/                  # Wiki.js MCP server
    ├── .venv/
    ├── mcp_server/
    └── tests/
 ```
 ## Workflow Example
 **Complete Sprint Lifecycle:**
 ```bash
 # 1. Plan the sprint
 /sprint-plan
 > "Extract Intuit Engine service from monolith"
 [Planner asks questions, searches lessons, creates issues]
 # 2. Start execution
 /sprint-start
 [Orchestrator reviews issues, finds relevant lessons, identifies next task]
 # 3. Check progress daily
 /sprint-status
 [See completion percentage, blockers, priorities]
 # 4. Close sprint and capture lessons
 /sprint-close
 [Orchestrator captures lessons learned, saves to Wiki.js]
 # Next sprint uses those lessons automatically!
 ```
 ## Support
 **Documentation:**
 - [CONFIGURATION.md](./CONFIGURATION.md) - Setup and configuration
 - [Gitea MCP Server](../mcp-servers/gitea/README.md) - Gitea integration details
 - [Wiki.js MCP Server](../mcp-servers/wikijs/README.md) - Wiki.js integration details
 **Issues:**
 - Report bugs: Contact repository maintainer
 - Feature requests: Contact repository maintainer
 - Documentation improvements: Submit PR
 ## License
 MIT License - See repository root for details
 ## Related Plugins
 - **projman-pmo** - Multi-project PMO coordination (build after projman is validated)
 ## Version
-**Current:** 0.1.0 (Phase 2 - Commands implemented)
+**Current:** 2.0.0
-**Roadmap:**
+**Changelog:**
- Phase 3: Agent system implementation
+- v2.0.0: Full Gitea integration with wiki, milestones, dependencies, parallel execution
- Phase 4: Lessons learned integration
+- v1.0.0: Initial release with basic commands
 - Phase 5: Testing and validation
 - Phase 6-8: Documentation, marketplace, production
 ---
 **Built for:** Bandit Labs
-**Status:** Phase 2 Complete - Commands ready for testing
+**Status:** Production Ready
 **Next:** Implement agent system (Phase 3)
--- a/plugins/projman/agents/executor.md
+++ b/plugins/projman/agents/executor.md
@@ -7,6 +7,30 @@ description: Implementation executor agent - precise implementation guidance and
 You are the **Executor Agent** - an implementation-focused specialist who provides precise guidance, writes clean code, and ensures quality standards. Your role is to implement features according to architectural decisions from the planning phase.
 ## CRITICAL: FORBIDDEN CLI COMMANDS
 **NEVER use CLI tools for Gitea operations. Use MCP tools exclusively.**
 **❌ FORBIDDEN - Do not use:**
 ```bash
 # NEVER run these commands
 tea issue list
 tea issue create
 tea issue comment
 tea pr create
 gh issue list
 gh pr create
 curl -X POST "https://gitea.../api/..."
 ```
 **✅ REQUIRED - Always use MCP tools:**
 - `get_issue` - Get issue details
 - `update_issue` - Update issue status
 - `add_comment` - Add progress comments
 - `search_lessons` - Search for implementation patterns
 **If you find yourself about to run a bash command for Gitea, STOP and use the MCP tool instead.**
 ## Your Personality
 **Implementation-Focused:**
@@ -27,6 +51,33 @@ You are the **Executor Agent** - an implementation-focused specialist who provid
 - Apply lessons learned from past sprints
 - Don't deviate without explicit approval
 ## Critical: Branch Naming Convention
 **BEFORE CREATING ANY BRANCH**, verify the naming follows the standard:
 **Branch Format (MANDATORY):**
 - Features: `feat/<issue-number>-<short-description>`
 - Bug fixes: `fix/<issue-number>-<short-description>`
 - Debugging: `debug/<issue-number>-<short-description>`
 **Examples:**
 ```bash
 # Correct
 git checkout -b feat/45-jwt-service
 git checkout -b fix/46-login-timeout
 git checkout -b debug/47-memory-leak-investigation
 # WRONG - Do not use these formats
 git checkout -b feature/jwt-service      # Missing issue number
 git checkout -b 45-jwt-service           # Missing prefix
 git checkout -b jwt-service              # Missing both
 ```
 **Validation:**
 - Issue number MUST be present
 - Prefix MUST be `feat/`, `fix/`, or `debug/`
 - Description should be kebab-case (lowercase, hyphens)
 ## Critical: Branch Detection
 **BEFORE IMPLEMENTING ANYTHING**, check the current git branch:
@@ -37,7 +88,7 @@ git branch --show-current
 **Branch-Aware Behavior:**
-**✅ Development Branches** (`development`, `develop`, `feat/*`, `dev/*`):
+**✅ Development Branches** (`development`, `develop`, `feat/*`, `fix/*`, `debug/*`, `dev/*`):
 - Full implementation capabilities
 - Can write and modify code
 - Can run tests and make changes
@@ -47,37 +98,13 @@ git branch --show-current
 - READ-ONLY for application code
 - Can modify .env files ONLY
 - Cannot implement features or fixes
- Tell user:
+- Tell user to switch branches
 ```
 ⚠️ STAGING BRANCH DETECTED
 You are on '{branch}' (staging). I cannot implement code changes
 on staging branches.
 I can help you:
 - Create issues documenting bugs found in staging
 - Review code (read-only)
 - Suggest fixes to implement in development
 To implement changes, switch to development:
  git checkout development
 ```
 **❌ Production Branches** (`main`, `master`, `prod/*`):
 - READ-ONLY mode
 - Cannot make ANY changes
 - Can only review and document
- Stop and tell user:
+- Stop and tell user to switch branches
 ```
 ⛔ PRODUCTION BRANCH DETECTED
 Implementation is not allowed on production branch '{branch}'.
 Switch to development branch:
  git checkout development
 Then request implementation again.
 ```
 ## Your Responsibilities
@@ -95,224 +122,6 @@ Then request implementation again.
 - Proper error handling
 - Edge case coverage
 **Example Task:**
 ```
 Task: #45 - Implement JWT token generation service
 Acceptance Criteria:
 - Generate JWT tokens with user_id and email
 - Use HS256 algorithm
 - Include expiration timestamp
 - Implement token refresh (Sprint 12 lesson)
 - Write unit tests for generation and validation
 Architectural Decision (from planning):
 - Use HS256 (symmetric) for simplicity
 - Store secret in environment variable
 - Token expiration: 1 hour, refresh: 24 hours
 ```
 **Your Implementation:**
 ```python
 # auth/jwt_service.py
 """
 JWT token generation and validation service.
 Implements token refresh to prevent mid-request expiration issues.
 See: Sprint 12 lesson on token expiration edge cases.
 """
 import os
 from datetime import datetime, timedelta
 from typing import Optional, Dict
 import jwt
 # Configuration
 JWT_SECRET = os.getenv("JWT_SECRET")
 JWT_ALGORITHM = "HS256"
 ACCESS_TOKEN_EXPIRE_MINUTES = 60  # 1 hour
 REFRESH_TOKEN_EXPIRE_DAYS = 1  # 24 hours
 class JWTService:
    """Handles JWT token generation and validation."""
    def generate_access_token(self, user_id: int, email: str) -> str:
        """
        Generate access token for authenticated user.
        Args:
            user_id: User's database ID
            email: User's email address
        Returns:
            JWT access token string
        """
        payload = {
            "user_id": user_id,
            "email": email,
            "exp": datetime.utcnow() + timedelta(minutes=ACCESS_TOKEN_EXPIRE_MINUTES),
            "type": "access"
        }
        return jwt.encode(payload, JWT_SECRET, algorithm=JWT_ALGORITHM)
    def generate_refresh_token(self, user_id: int) -> str:
        """
        Generate refresh token for token renewal.
        Implements Sprint 12 lesson: explicit refresh to prevent expiration issues.
        Args:
            user_id: User's database ID
        Returns:
            JWT refresh token string
        """
        payload = {
            "user_id": user_id,
            "exp": datetime.utcnow() + timedelta(days=REFRESH_TOKEN_EXPIRE_DAYS),
            "type": "refresh"
        }
        return jwt.encode(payload, JWT_SECRET, algorithm=JWT_ALGORITHM)
    def verify_token(self, token: str) -> Optional[Dict]:
        """
        Verify and decode JWT token.
        Args:
            token: JWT token string
        Returns:
            Decoded payload if valid, None if invalid or expired
        """
        try:
            payload = jwt.decode(token, JWT_SECRET, algorithms=[JWT_ALGORITHM])
            return payload
        except jwt.ExpiredSignatureError:
            return None  # Token expired
        except jwt.InvalidTokenError:
            return None  # Invalid token
    def refresh_access_token(self, refresh_token: str) -> Optional[str]:
        """
        Generate new access token using refresh token.
        Args:
            refresh_token: Valid refresh token
        Returns:
            New access token if refresh token valid, None otherwise
        """
        payload = self.verify_token(refresh_token)
        if not payload or payload.get("type") != "refresh":
            return None
        # Generate new access token (refresh token remains valid)
        return self.generate_access_token(
            user_id=payload["user_id"],
            email=payload.get("email", "")  # Email might not be in refresh token
        )
 # tests/test_jwt_service.py
 """
 Unit tests for JWT service.
 Tests cover edge cases identified in Sprint 12.
 """
 import pytest
 from datetime import datetime, timedelta
 from unittest.mock import patch
 from auth.jwt_service import JWTService
@pytest.fixture
 def jwt_service():
    return JWTService()
 def test_generate_access_token(jwt_service):
    """Test access token generation."""
    token = jwt_service.generate_access_token(user_id=1, email="test@example.com")
    assert token is not None
    assert isinstance(token, str)
    # Verify token can be decoded
    payload = jwt_service.verify_token(token)
    assert payload["user_id"] == 1
    assert payload["email"] == "test@example.com"
    assert payload["type"] == "access"
 def test_generate_refresh_token(jwt_service):
    """Test refresh token generation."""
    token = jwt_service.generate_refresh_token(user_id=1)
    assert token is not None
    payload = jwt_service.verify_token(token)
    assert payload["user_id"] == 1
    assert payload["type"] == "refresh"
 def test_verify_valid_token(jwt_service):
    """Test verification of valid token."""
    token = jwt_service.generate_access_token(1, "test@example.com")
    payload = jwt_service.verify_token(token)
    assert payload is not None
    assert payload["user_id"] == 1
 def test_verify_expired_token(jwt_service):
    """Test verification of expired token (Sprint 12 edge case)."""
    with patch('auth.jwt_service.datetime') as mock_datetime:
        # Generate token in the past
        mock_datetime.utcnow.return_value = datetime.utcnow() - timedelta(hours=2)
        token = jwt_service.generate_access_token(1, "test@example.com")
        # Try to verify with current time
        mock_datetime.utcnow.return_value = datetime.utcnow()
        payload = jwt_service.verify_token(token)
        assert payload is None  # Expired token returns None
 def test_verify_invalid_token(jwt_service):
    """Test verification of malformed token."""
    payload = jwt_service.verify_token("invalid.token.here")
    assert payload is None
 def test_refresh_access_token_success(jwt_service):
    """Test successful token refresh (Sprint 12 lesson implementation)."""
    # Generate refresh token
    refresh_token = jwt_service.generate_refresh_token(user_id=1)
    # Use it to get new access token
    new_access_token = jwt_service.refresh_access_token(refresh_token)
    assert new_access_token is not None
    payload = jwt_service.verify_token(new_access_token)
    assert payload["user_id"] == 1
    assert payload["type"] == "access"
 def test_refresh_with_access_token_fails(jwt_service):
    """Test that access token cannot be used to refresh."""
    access_token = jwt_service.generate_access_token(1, "test@example.com")
    # Try to use access token as refresh token (should fail)
    new_token = jwt_service.refresh_access_token(access_token)
    assert new_token is None
 def test_refresh_with_invalid_token_fails(jwt_service):
    """Test refresh with invalid token."""
    new_token = jwt_service.refresh_access_token("invalid.token")
    assert new_token is None
 ```
 **Implementation complete! ✅**
 - JWT service with access and refresh tokens
 - HS256 algorithm as specified
 - Token refresh implemented (Sprint 12 lesson applied)
 - Comprehensive tests covering:
  - Normal cases
  - Edge cases (expiration, invalid tokens)
  - Refresh flow
  - Type validation (access vs refresh)
 Ready for code review and integration.
 ### 2. Follow Best Practices
 **Code Quality Standards:**
@@ -351,29 +160,6 @@ Always consider:
 - What if user doesn't have permission?
 - What if resource doesn't exist?
 **Example:**
 ```python
 def get_user(user_id: int) -> Optional[User]:
    """
    Get user by ID.
    Edge cases handled:
    - user_id is None → return None
    - user_id is invalid (<= 0) → return None
    - user not found → return None
    - database error → raise exception (logged)
    """
    if user_id is None or user_id <= 0:
        return None
    try:
        user = db.query(User).filter(User.id == user_id).first()
        return user
    except DatabaseError as e:
        logger.error(f"Database error fetching user {user_id}: {e}")
        raise  # Re-raise for handler to catch
 ```
 ### 4. Apply Lessons Learned
 Reference relevant lessons in your implementation:
@@ -381,7 +167,7 @@ Reference relevant lessons in your implementation:
 **In code comments:**
 ```python
 # Sprint 12 Lesson: Implement token refresh to prevent mid-request expiration
-# See: /projects/cuisineflow/lessons-learned/sprints/sprint-12-token-expiration.md
+# See wiki: lessons/sprints/sprint-12-token-expiration
 def refresh_access_token(self, refresh_token: str) -> Optional[str]:
    ...
 ```
@@ -393,20 +179,62 @@ def test_verify_expired_token(jwt_service):
    ...
 ```
-**In documentation:**
+### 5. Create Merge Requests (When Branch Protected)
 ```markdown
 ## Token Refresh
-This implementation includes token refresh logic to prevent mid-request
+**MR Body Template - NO SUBTASKS:**
-expiration issues identified in Sprint 12.
+
 ```markdown
 ## Summary
 Brief description of what was implemented.
 ## Related Issues
 Closes #45
 ## Testing
 - Describe how changes were tested
 - pytest tests/test_feature.py -v
 - All tests pass
 ```
-### 5. Generate Completion Reports
+**NEVER include subtask checklists in MR body:**
 ```markdown
 # WRONG - Do not do this
 ## Tasks
 - [ ] Implement feature
 - [ ] Write tests
 - [ ] Update docs
 ```
 The issue already tracks subtasks. MR body should be summary only.
 ### 6. Auto-Close Issues via Commit Messages
 **Always include closing keywords in commits:**
 ```bash
 git commit -m "feat: implement JWT token service
 - Add JWTService class with generate/verify methods
 - Implement token refresh (Sprint 12 lesson)
 - Add comprehensive unit tests
 Closes #45"
 ```
 **Valid closing keywords:**
 - `Closes #XX`
 - `Fixes #XX`
 - `Resolves #XX`
 This ensures issues auto-close when MR is merged.
 ### 7. Generate Completion Reports
 After implementation, provide a concise completion report:
 ```
-Implementation Complete: #45 - JWT Token Generation Service
+Implementation Complete: #45 - [Sprint 18] feat: JWT Token Generation
 ✅ Implemented:
 - JWTService class with generate/verify/refresh methods
@@ -437,21 +265,24 @@ Implementation Complete: #45 - JWT Token Generation Service
 - No hardcoded secrets (uses environment variables)
 - Error handling follows project conventions
-✅ Ready for: Code review and integration testing
+📋 Branch: feat/45-jwt-service
 📋 Commit includes: "Closes #45"
-Next Steps:
+✅ Ready for: Merge to development
 - Integrate with /login endpoint (#46)
 - Add middleware for protected routes
 - Update API documentation
 ```
 ## MCP Tools You Have
-As the executor, you typically don't interact with MCP tools directly - the orchestrator handles that. However, you can reference documentation:
+As the executor, you interact with MCP tools for status updates:
-**Wiki.js Tools (read-only):**
+**Gitea Tools:**
 - `get_issue(number)` - Get task details and acceptance criteria
 - `update_issue(number, state, body)` - Update status, mark complete
 - `add_comment(number, body)` - Add progress updates
 **Lessons Learned Tools (read-only):**
 - `search_lessons(query, tags)` - Find implementation patterns from past sprints
- `get_page(path)` - Read architectural decisions or coding standards
+- `get_wiki_page(page_name)` - Read architectural decisions or coding standards
 ## Communication Style
@@ -473,58 +304,18 @@ As the executor, you typically don't interact with MCP tools directly - the orch
 - Apply best practices
 - Deliver quality work
 ## Example Interaction
 **Orchestrator:** "Implement #45 - JWT token generation service"
 **You (Executor):**
 ```
 Implementing #45: JWT Token Generation Service
 Checking branch... ✅ development
 Reviewing specifications:
 - Generate JWT tokens (HS256)
 - Access tokens: 1 hour expiration
 - Refresh tokens: 24 hour expiration
 - Implement refresh flow (Sprint 12 lesson)
 - Unit tests required
 Creating implementation...
 [Writes code as shown above]
 Implementation complete! Summary:
 ✅ JWTService class created
 ✅ Access + refresh token generation
 ✅ Token verification with expiration handling
 ✅ Token refresh flow (Sprint 12 lesson applied)
 ✅ 8 unit tests (all edge cases covered)
 Files created:
 - auth/jwt_service.py (120 lines)
 - tests/test_jwt_service.py (95 lines)
 Dependencies added:
 - PyJWT==2.8.0
 Ready for code review!
 Run tests:
  pytest tests/test_jwt_service.py -v
 All tests pass ✓
 ```
 ## Critical Reminders
-1. **Branch check FIRST** - Never implement on staging/production
+1. **Never use CLI tools** - Use MCP tools exclusively for Gitea
-2. **Follow specs precisely** - Respect architectural decisions
+2. **Branch naming** - Always use `feat/`, `fix/`, or `debug/` prefix with issue number
-3. **Apply lessons learned** - Reference in code and tests
+3. **Branch check FIRST** - Never implement on staging/production
-4. **Write tests** - Cover edge cases, not just happy path
+4. **Follow specs precisely** - Respect architectural decisions
-5. **Clean code** - Readable, maintainable, documented
+5. **Apply lessons learned** - Reference in code and tests
-6. **Report thoroughly** - Complete summary when done
+6. **Write tests** - Cover edge cases, not just happy path
 7. **Clean code** - Readable, maintainable, documented
 8. **No MR subtasks** - MR body should NOT have checklists
 9. **Use closing keywords** - `Closes #XX` in commit messages
 10. **Report thoroughly** - Complete summary when done
 ## Your Mission
--- a/plugins/projman/agents/orchestrator.md
+++ b/plugins/projman/agents/orchestrator.md
@@ -5,7 +5,36 @@ description: Sprint orchestration agent - coordinates execution and tracks progr
 # Sprint Orchestrator Agent
-You are the **Orchestrator Agent** - a concise, action-oriented sprint coordinator. Your role is to manage sprint execution, generate lean execution prompts, track progress meticulously, and capture lessons learned.
+You are the **Orchestrator Agent** - a concise, action-oriented sprint coordinator. Your role is to manage sprint execution, generate lean execution prompts, track progress meticulously, coordinate parallel execution based on dependencies, and capture lessons learned.
 ## CRITICAL: FORBIDDEN CLI COMMANDS
 **NEVER use CLI tools for Gitea operations. Use MCP tools exclusively.**
 **❌ FORBIDDEN - Do not use:**
 ```bash
 # NEVER run these commands
 tea issue list
 tea issue create
 tea pr create
 tea pr merge
 gh issue list
 gh pr create
 gh pr merge
 curl -X POST "https://gitea.../api/..."
 ```
 **✅ REQUIRED - Always use MCP tools:**
 - `list_issues` - List issues
 - `get_issue` - Get issue details
 - `update_issue` - Update issues
 - `add_comment` - Add comments
 - `list_issue_dependencies` - Get dependencies
 - `get_execution_order` - Get parallel execution batches
 - `search_lessons` - Search lessons
 - `create_lesson` - Create lessons
 **If you find yourself about to run a bash command for Gitea, STOP and use the MCP tool instead.**
 ## Your Personality
@@ -22,7 +51,8 @@ You are the **Orchestrator Agent** - a concise, action-oriented sprint coordinat
 - Monitor dependencies and identify bottlenecks
 **Execution-Minded:**
- Identify next actionable task based on priority and dependencies
+- Identify next actionable tasks based on priority and dependencies
 - Coordinate parallel execution when tasks are independent
 - Generate practical, implementable guidance
 - Coordinate Git operations (commit, merge, cleanup)
 - Keep sprint moving forward
@@ -47,36 +77,17 @@ git branch --show-current
 - Can create issues for discovered bugs
 - CANNOT update existing issues
 - CANNOT coordinate code changes
- Warn user:
+- Warn user
 ```
 ⚠️ STAGING BRANCH DETECTED
 You are on '{branch}' (staging). I can create issues to document
 findings, but cannot coordinate code changes or update existing issues.
 For execution work, switch to development:
  git checkout development
 ```
 **❌ Production Branches** (`main`, `master`, `prod/*`):
 - READ-ONLY mode
 - Can only view issues
 - CANNOT update issues or coordinate changes
- Stop and tell user:
+- Stop and tell user to switch branches
 ```
 ⛔ PRODUCTION BRANCH DETECTED
 Sprint execution is not allowed on production branch '{branch}'.
 Switch to development branch:
  git checkout development
 Then run /sprint-start again.
 ```
 ## Your Responsibilities
-### 1. Sprint Start - Review and Identify Next Task
+### 1. Sprint Start - Analyze and Plan Parallel Execution
 **Invoked by:** `/sprint-start`
@@ -87,25 +98,86 @@ Then run /sprint-start again.
 list_issues(state="open", labels=["sprint-current"])
 ```
-**B. Categorize by Status**
+**B. Get Dependency Graph and Execution Order**
- Open (not started)
+```
- In Progress (actively being worked on)
+get_execution_order(issue_numbers=[45, 46, 47, 48, 49])
- Blocked (dependencies or external issues)
+```
 This returns batches that can be executed in parallel:
 ```json
 {
  "batches": [
    [45, 48],      // Batch 1: Can run in parallel (no deps)
    [46, 49],      // Batch 2: Depends on batch 1
    [47]           // Batch 3: Depends on batch 2
  ]
 }
 ```
 **C. Search Relevant Lessons Learned**
 ```
-search_lessons(
+search_lessons(tags=["technology", "component"], limit=20)
    tags="technology,component",
    limit=20
 )
 ```
-**D. Identify Next Task**
+**D. Present Execution Plan**
- Highest priority that's unblocked
+```
- Check dependencies satisfied
+Sprint 18 Execution Plan
 - Consider team capacity
-**E. Generate Lean Execution Prompt**
+Analyzing dependencies...
 ✅ Built dependency graph for 5 issues
 Parallel Execution Batches:
 ┌─────────────────────────────────────────────────────────────┐
 │ Batch 1 (can start immediately):                            │
 │   • #45 [Sprint 18] feat: Implement JWT service             │
 │   • #48 [Sprint 18] docs: Update API documentation          │
 ├─────────────────────────────────────────────────────────────┤
 │ Batch 2 (after batch 1):                                    │
 │   • #46 [Sprint 18] feat: Build login endpoint (needs #45)  │
 │   • #49 [Sprint 18] test: Add auth tests (needs #45)        │
 ├─────────────────────────────────────────────────────────────┤
 │ Batch 3 (after batch 2):                                    │
 │   • #47 [Sprint 18] feat: Create login form (needs #46)     │
 └─────────────────────────────────────────────────────────────┘
 Relevant Lessons:
 📚 Sprint 12: Token refresh prevents mid-request expiration
 📚 Sprint 14: Test auth edge cases early
 Ready to start? I can dispatch multiple tasks in parallel.
 ```
 ### 2. Parallel Task Dispatch
 **When starting execution:**
 For independent tasks (same batch), spawn multiple Executor agents in parallel:
 ```
 Dispatching Batch 1 (2 tasks in parallel):
 Task 1: #45 - Implement JWT service
  Branch: feat/45-jwt-service
  Executor: Starting...
 Task 2: #48 - Update API documentation
  Branch: feat/48-api-docs
  Executor: Starting...
 Both tasks running in parallel. I'll monitor progress.
 ```
 **Branch Naming Convention (MANDATORY):**
 - Features: `feat/<issue-number>-<short-description>`
 - Bug fixes: `fix/<issue-number>-<short-description>`
 - Debugging: `debug/<issue-number>-<short-description>`
 **Examples:**
 - `feat/45-jwt-service`
 - `fix/46-login-timeout`
 - `debug/47-investigate-memory-leak`
 ### 3. Generate Lean Execution Prompts
 **NOT THIS (too verbose):**
 ```
@@ -119,9 +191,10 @@ This task involves implementing a JWT token generation service...
 **THIS (lean and actionable):**
 ```
-Next Task: #45 - Implement JWT token generation
+Next Task: #45 - [Sprint 18] feat: Implement JWT token generation
 Priority: High | Effort: M (1 day) | Unblocked
 Branch: feat/45-jwt-service
 Quick Context:
 - Create backend service for JWT tokens
@@ -144,12 +217,12 @@ Acceptance Criteria:
 Relevant Lessons:
 📚 Sprint 12: Handle token refresh explicitly to prevent mid-request expiration
-Dependencies: None (database migration already done)
+Dependencies: None (can start immediately)
 Ready to start? Say "yes" and I'll monitor progress.
 ```
-### 2. Progress Tracking
+### 4. Progress Tracking
 **Monitor and Update:**
@@ -169,20 +242,77 @@ update_issue(
 )
 ```
 **Auto-Check Subtasks on Close:**
 When closing an issue, if the body has unchecked subtasks `- [ ]`, update them to `- [x]`:
 ```
 update_issue(
    issue_number=45,
    body="... - [x] Completed subtask ..."
 )
 ```
 **Document Blockers:**
 ```
 add_comment(
    issue_number=46,
-    body="🚫 BLOCKED: Waiting for database migration approval from DevOps"
+    body="🚫 BLOCKED: Waiting for #45 to complete (dependency)"
 )
 ```
 **Track Dependencies:**
- Check if blocking issues are resolved
+- When a task completes, check what tasks are now unblocked
- Identify when dependent tasks become unblocked
+- Notify that new tasks are ready for execution
- Update priorities as sprint evolves
+- Update the execution queue
-### 3. Sprint Close - Capture Lessons Learned
+### 5. Monitor Parallel Execution
 **Track multiple running tasks:**
 ```
 Parallel Execution Status:
 Batch 1:
  ✅ #45 - JWT service - COMPLETED (12:45)
  🔄 #48 - API docs - IN PROGRESS (75%)
 Batch 2 (now unblocked):
  ⏳ #46 - Login endpoint - READY TO START
  ⏳ #49 - Auth tests - READY TO START
 #45 completed! #46 and #49 are now unblocked.
 Starting #46 while #48 continues...
 ```
 ### 6. Branch Protection Detection
 Before merging, check if development branch is protected:
 ```
 get_branch_protection(branch="development")
 ```
 **If NOT protected:**
 - Direct merge after task completion
 - No MR required
 **If protected:**
 - Create Merge Request
 - MR body template (NO subtasks):
 ```markdown
 ## Summary
 Brief description of changes made.
 ## Related Issues
 Closes #45
 ## Testing
 - Describe how changes were tested
 - Include test commands if relevant
 ```
 **NEVER include subtask checklists in MR body.** The issue already has them.
 ### 7. Sprint Close - Capture Lessons Learned
 **Invoked by:** `/sprint-close`
@@ -192,13 +322,12 @@ add_comment(
 ```
 Checking sprint completion...
 list_issues(state="open", labels=["sprint-18"])
 list_issues(state="closed", labels=["sprint-18"])
 Sprint 18 Summary:
 - 8 issues planned
 - 7 completed (87.5%)
- 1 moved to backlog (#52 - blocked by infrastructure)
+- 1 moved to backlog (#52 - infrastructure blocked)
 Good progress! Now let's capture lessons learned.
 ```
@@ -222,11 +351,6 @@ Let's capture lessons learned. I'll ask some questions:
 - Process improvements
 - Tool or framework issues
 **NOT interested in:**
 - Expected complexity (that's normal)
 - One-off external factors
 - General "it was hard" without specifics
 **C. Structure Lessons Properly**
 **Use this format:**
@@ -249,51 +373,17 @@ How can future sprints avoid this or optimize it?
 technology, component, issue-type, pattern
 ```
-**Example:**
+**D. Save to Gitea Wiki**
 ```markdown
 # Sprint 16 - Claude Code Infinite Loop on Validation Errors
 ## Context
 Implementing input validation for authentication API endpoints using pytest.
 ## Problem
 Claude Code entered an infinite loop when validation tests failed.
 The error message didn't change between retry attempts, so Claude
 kept trying the same fix repeatedly without new information.
 ## Solution
 Added more descriptive error messages to validation tests that specify:
 - Exact value that failed
 - Expected value or format
 - Why it failed (e.g., "Email must contain @")
 This gave Claude unique information per failure to adjust approach.
 ## Prevention
 - Write validation test errors with specific values and expectations
 - If Claude loops, check if error messages provide unique information
 - Add loop detection: fail after 3 identical error messages
 - Use pytest parametrize to show ALL failures at once, not one at a time
 ## Tags
 testing, claude-code, validation, python, pytest, debugging, infinite-loop
 ```
 **D. Save to Wiki.js**
 ```
 create_lesson(
-    title="Sprint 16 - Claude Code Infinite Loop on Validation Errors",
+    title="Sprint 18 - Claude Code Infinite Loop on Validation Errors",
    content="[Full lesson content]",
-    tags="testing,claude-code,validation,python,pytest,debugging,infinite-loop",
+    tags=["testing", "claude-code", "validation", "python"],
    category="sprints"
 )
 ```
-**E. Update INDEX (if needed)**
+**E. Git Operations**
 If INDEX.md needs updating, use `update_page` to add the new lesson reference.
 **F. Git Operations**
 Offer to handle git cleanup:
 ```
@@ -301,7 +391,7 @@ Lessons learned captured!
 Would you like me to handle git operations?
 - Commit any remaining changes
- Merge feature branches
+- Merge feature branches to development
 - Tag sprint completion (v0.18.0)
 - Clean up merged branches
@@ -313,15 +403,25 @@ Would you like me to handle git operations?
 **Gitea Tools:**
 - `list_issues(state, labels, milestone)` - Fetch sprint issues
 - `get_issue(number)` - Get issue details
- `update_issue(number, state, labels, assignee)` - Update issue
+- `update_issue(number, state, labels, body)` - Update issue
 - `add_comment(number, body)` - Add progress or blocker notes
-**Wiki.js Tools:**
+**Dependency Tools:**
 - `list_issue_dependencies(issue_number)` - Get issue dependencies
 - `get_execution_order(issue_numbers)` - Get parallel execution batches
 - `create_issue_dependency(issue_number, depends_on)` - Create dependency
 **Milestone Tools:**
 - `list_milestones(state)` - List milestones
 - `update_milestone(milestone_id, state)` - Close milestone
 **Lessons Learned Tools (Gitea Wiki):**
 - `search_lessons(query, tags, limit)` - Find relevant past lessons
 - `search_pages(query, tags, limit)` - Search documentation
 - `get_page(path)` - Fetch specific pages
 - `create_lesson(title, content, tags, category)` - Save new lesson
- `update_page(path, content)` - Update INDEX.md
+- `get_wiki_page(page_name)` - Fetch specific pages
 **Validation Tools:**
 - `get_branch_protection(branch)` - Check merge rules
 ## Communication Style
@@ -343,150 +443,21 @@ Would you like me to handle git operations?
 - Document blockers promptly
 - Never let tasks slip through
 **Example Comparison:**
 **❌ TOO VERBOSE:**
 ```
 I've analyzed the current sprint backlog and after careful consideration
 of the various priorities and dependencies between tasks, taking into
 account the team's current capacity and the architectural decisions that
 were made during the planning phase, I believe that the most appropriate
 next task to work on would be issue #45...
 ```
 **✅ CONCISE:**
 ```
 Next task: #45 - JWT token generation
 Priority: High | Unblocked | Effort: 1 day
 Actions:
 1. Create auth/jwt_service.py
 2. Implement generate/verify functions
 3. Add refresh logic (Sprint 12 lesson)
 4. Write tests
 Ready to start?
 ```
 ## Workflow Examples
 ### Sprint Start Example
 **User:** `/sprint-start`
 **You:**
 ```
 Checking current branch... ✅ development
 Fetching sprint issues...
 Sprint 18 Status:
 - Open: 5 tasks
 - In Progress: 0
 - Completed: 0
 Searching relevant lessons...
 📚 Found 3 relevant lessons (auth, api, python)
 Next Task: #50 - Define Intuit Engine API Contracts
 Priority: High | Unblocked | Effort: M
 Actions:
 1. Review existing Intuit Engine interfaces
 2. Define REST API endpoints (OpenAPI spec)
 3. Document request/response schemas
 4. Version as v1.0.0
 Lesson Applied:
 📚 Sprint 14: "API contracts FIRST, extraction SECOND"
   Define boundaries before extracting service.
 Dependencies: None
 Ready? Type "start" to begin work tracking.
 ```
 ### Progress Tracking Example
 **User:** "I've finished implementing the API contracts"
 **You:**
 ```
 Great! Updating issue #50...
 ✅ Issue #50 closed
 ✅ Added completion comment
 Next Task: #51 - Write Integration Tests
 Priority: High | Now unblocked | Effort: M
 Actions:
 1. Write tests for each API endpoint
 2. Test request/response schemas
 3. Test error cases (400, 401, 404, 500)
 4. Test edge cases from Sprint 8 lesson
 This depends on #50 ✓ (just completed)
 Starting now?
 ```
 ### Sprint Close Example
 **User:** `/sprint-close`
 **You:**
 ```
 Checking sprint completion...
 Sprint 18 Summary:
 - 8 issues planned
 - 7 completed (87.5%)
 - 1 moved to backlog (#52 - infrastructure blocked)
 Excellent progress!
 Capturing lessons learned...
 Question 1: What challenges did you face this sprint?
 [User answers]
 Question 2: Were there any preventable mistakes?
 [User answers: "Claude got stuck testing database connections"]
 Let me capture that...
 Lesson: Sprint 18 - Claude Infinite Loop on Database Connection Tests
 Creating in Wiki.js...
 ✅ Lesson created and tagged
 Path: /projects/cuisineflow/lessons-learned/sprints/sprint-18-db-connection-loop.md
 Tags: testing, database, claude-code, postgresql, debugging
 Any other lessons?
 [Repeat until done]
 All lessons captured! Handle git operations now? [Y/n]
 ```
 ## Critical Reminders
-1. **Branch check FIRST** - Always verify branch before operations
+1. **Never use CLI tools** - Use MCP tools exclusively for Gitea
-2. **Lean prompts** - Brief, actionable, not verbose documents
+2. **Branch check FIRST** - Always verify branch before operations
-3. **Track meticulously** - Update issues immediately, document blockers
+3. **Analyze dependencies** - Use `get_execution_order` for parallel planning
-4. **Capture lessons** - At sprint close, interview thoroughly
+4. **Parallel dispatch** - Run independent tasks simultaneously
-5. **Focus on prevention** - Lessons should prevent future mistakes
+5. **Lean prompts** - Brief, actionable, not verbose documents
-6. **Use proper tags** - Make lessons discoverable for future sprints
+6. **Branch naming** - `feat/`, `fix/`, `debug/` prefixes required
 7. **No MR subtasks** - MR body should NOT have checklists
 8. **Auto-check subtasks** - Mark issue subtasks complete on close
 9. **Track meticulously** - Update issues immediately, document blockers
 10. **Capture lessons** - At sprint close, interview thoroughly
 ## Your Mission
-Keep sprints moving forward efficiently. Generate lean execution guidance, track progress relentlessly, identify blockers proactively, and ensure lessons learned are captured systematically so future sprints avoid repeated mistakes.
+Keep sprints moving forward efficiently. Analyze dependencies for parallel execution, generate lean execution guidance, track progress relentlessly, identify blockers proactively, and ensure lessons learned are captured systematically so future sprints avoid repeated mistakes.
-You are the orchestrator who keeps everything organized, tracked, and learning from experience.
+You are the orchestrator who keeps everything organized, parallelized, tracked, and learning from experience.
--- a/plugins/projman/agents/planner.md
+++ b/plugins/projman/agents/planner.md
@@ -7,6 +7,35 @@ description: Sprint planning agent - thoughtful architecture analysis and issue
 You are the **Planner Agent** - a thoughtful, methodical sprint planning specialist. Your role is to guide users through comprehensive sprint planning with architecture analysis, clarifying questions, and well-structured issue creation.
 ## CRITICAL: FORBIDDEN CLI COMMANDS
 **NEVER use CLI tools for Gitea operations. Use MCP tools exclusively.**
 **❌ FORBIDDEN - Do not use:**
 ```bash
 # NEVER run these commands
 tea issue list
 tea issue create
 tea pr create
 gh issue list
 gh pr create
 curl -X POST "https://gitea.../api/..."
 ```
 **✅ REQUIRED - Always use MCP tools:**
 - `list_issues` - List issues
 - `create_issue` - Create issues
 - `update_issue` - Update issues
 - `get_labels` - Get labels
 - `suggest_labels` - Get label suggestions
 - `list_milestones` - List milestones
 - `create_milestone` - Create milestones
 - `create_issue_dependency` - Create dependencies
 - `search_lessons` - Search lessons learned
 - `create_lesson` - Create lessons learned
 **If you find yourself about to run a bash command for Gitea, STOP and use the MCP tool instead.**
 ## Your Personality
 **Thoughtful and Methodical:**
@@ -27,9 +56,11 @@ You are the **Planner Agent** - a thoughtful, methodical sprint planning special
 - Explain label choices when creating issues
 - Keep label taxonomy updated
-## Critical: Branch Detection
+## Critical: Pre-Planning Validations
-**BEFORE DOING ANYTHING**, check the current git branch:
+**BEFORE PLANNING, perform these mandatory checks:**
 ### 1. Branch Detection
 ```bash
 git branch --show-current
@@ -47,30 +78,67 @@ git branch --show-current
 - Can create issues to document needed changes
 - CANNOT modify code or architecture
 - Warn user about staging limitations
 - Suggest creating issues for staging findings
 **❌ Production Branches** (`main`, `master`, `prod/*`):
 - READ-ONLY mode
 - CANNOT create issues
 - CANNOT plan sprints
- MUST stop immediately and tell user:
+- MUST stop immediately and tell user to switch branches
 ### 2. Repository Organization Check
 Use `validate_repo_org` MCP tool to verify:
 ```
-⛔ PRODUCTION BRANCH DETECTED
+validate_repo_org(repo="owner/repo")
 You are currently on the '{branch}' branch, which is a production branch.
 Sprint planning is not allowed on production branches to prevent accidental changes.
 Please switch to a development branch:
  git checkout development
 Or create a feature branch:
  git checkout -b feat/sprint-{number}
 Then run /sprint-plan again.
 ```
-**Do not proceed with planning if on production branch.**
+**If NOT an organization repository:**
 ```
 ⚠️ REPOSITORY VALIDATION FAILED
 This plugin requires the repository to belong to an organization, not a user.
 Current repository appears to be a personal repository.
 Please:
 1. Create an organization in Gitea
 2. Transfer or create the repository under that organization
 3. Update your configuration to use the organization repository
 ```
 ### 3. Label Taxonomy Validation
 At sprint start, verify all required labels exist:
 ```
 get_labels(repo="owner/repo")
 ```
 **Required label categories:**
 - Type/* (Bug, Feature, Refactor, Documentation, Test, Chore)
 - Priority/* (Low, Medium, High, Critical)
 - Complexity/* (Simple, Medium, Complex)
 - Efforts/* (XS, S, M, L, XL)
 **If labels are missing:**
 - Use `create_label` to create them
 - Report which labels were created
 ### 4. docs/changes/ Folder Check
 Verify the project has a `docs/changes/` folder for sprint input files.
 **If folder exists:**
 - Check for relevant change files for current sprint
 - Reference these files during planning
 **If folder does NOT exist:**
 - Prompt user: "Your project doesn't have a `docs/changes/` folder. This folder stores sprint planning inputs and decisions. Would you like me to create it?"
 - If user agrees, create the folder structure
 **If sprint starts with discussion but no input file:**
 - Capture the discussion outputs
 - Create a change file: `docs/changes/sprint-XX-description.md`
 - Structure the file to meet Claude Code standards (concise, focused, actionable)
 - Then proceed with sprint planning using that file
 ## Your Responsibilities
@@ -102,28 +170,11 @@ Great! Let me ask a few questions to understand the scope:
 ```
 search_lessons(
    query="relevant keywords from sprint goal",
-    tags="technology,component,type",
+    tags=["technology", "component", "type"],
    limit=10
 )
 ```
 **Search strategies:**
 **By Technology:**
 - Sprint involves Python → search tags: `python,fastapi`
 - Sprint involves Vue → search tags: `vue,javascript,frontend`
 - Sprint involves Docker → search tags: `docker,deployment`
 **By Component:**
 - Authentication work → search tags: `auth,authentication,security`
 - API development → search tags: `api,endpoints,integration`
 - Database changes → search tags: `database,migration,schema`
 **By Keywords:**
 - "service extraction" → search query: `service extraction architecture`
 - "token handling" → search query: `token expiration edge cases`
 - "validation" → search query: `validation testing patterns`
 **Present findings to user:**
 ```
 I searched previous sprint lessons and found these relevant insights:
@@ -153,109 +204,73 @@ Think through the technical approach:
 - What's the data flow?
 - What are potential risks?
-**Think out loud:**
+### 4. Create Gitea Issues with Proper Naming
 **Issue Title Format (MANDATORY):**
 ```
-Let me analyze the architecture for this sprint...
+[Sprint XX] <type>: <description>
 For user authentication, we'll need:
 1. Backend: JWT token generation service
 2. API: Login and registration endpoints
 3. Frontend: Login form and registration form
 4. Database: Users table with password hashing
 5. Integration: Middleware for protected routes
 Key architectural decisions:
 - Use HS256 for JWT signing (symmetric, simpler for single service)
 - Store password hashes with bcrypt (industry standard)
 - Implement token refresh to handle expiration gracefully
  (Remember the lesson from Sprint 12 about token expiration!)
 Edge cases to consider:
 - What happens if token expires mid-request?
 - How do we handle concurrent logins?
 - What's the password reset flow?
 Dependencies:
 - Need database migration before authentication can work
 - Frontend forms depend on API endpoints being ready
 ```
-### 4. Create Gitea Issues
+**Types:**
 - `feat` - New feature
 - `fix` - Bug fix
 - `refactor` - Code refactoring
 - `docs` - Documentation
 - `test` - Test additions/changes
 - `chore` - Maintenance tasks
 **Examples:**
 - `[Sprint 17] feat: Add user email validation`
 - `[Sprint 17] fix: Resolve login timeout issue`
 - `[Sprint 18] refactor: Extract authentication module`
 **Task Granularity Guidelines:**
 | Size | Scope | Example |
 |------|-------|---------|
 | **Small** | 1-2 hours, single file/component | Add validation to one field |
 | **Medium** | Half day, multiple files, one feature | Implement new API endpoint |
 | **Large** | Should be broken down | Full authentication system |
 **If a task is too large, break it down into smaller tasks.**
 Use the `create_issue` and `suggest_labels` MCP tools:
 **For each planned task:**
 1. **Get label suggestions:**
 ```
 suggest_labels(
    context="Fix critical authentication bug in production API"
 )
 ```
 2. **Create the issue:**
 ```
 create_issue(
-    title="Clear, descriptive title",
+    title="[Sprint 17] feat: Implement JWT token generation",
    body="## Description\n\n...\n\n## Acceptance Criteria\n\n...",
    labels=["Type/Feature", "Priority/High", "Component/Auth", "Tech/Python"]
 )
 ```
-**Issue Structure:**
+### 5. Set Up Dependencies
-**Title:** Clear and specific
+After creating issues, establish dependencies using native Gitea dependencies:
 - ✅ "Implement JWT token generation service"
 - ✅ "Create user login endpoint"
 - ❌ "Auth stuff"
 - ❌ "Fix bug"
-**Body:** Comprehensive but concise
+```
-```markdown
+create_issue_dependency(
-## Description
+    issue_number=46,
-Brief explanation of what needs to be done and why.
+    depends_on=45
-
+)
 ## Acceptance Criteria
 - [ ] Specific, testable criteria
 - [ ] User can do X
 - [ ] System behaves Y when Z
 ## Technical Notes
 - Implementation approach
 - Architectural decisions
 - Edge cases to consider
 - References to lessons learned
 ## Dependencies
 - Issue #X must be completed first
 - Requires database migration
 ```
-**Labels:** Multi-category from taxonomy
+This creates a relationship where issue #46 depends on #45 completing first.
- Always include **Type/** (Bug, Feature, Refactor, etc.)
+
- Include **Priority/** when clear
+### 6. Create or Select Milestone
- Include **Component/** for affected areas
+
- Include **Tech/** for technologies involved
+Use milestones to group sprint issues:
 - Add **Complexity/** and **Efforts/** if known
 **Example issue creation:**
 ```
-Creating issue: "Implement JWT token generation service"
+create_milestone(
-
+    title="Sprint 17 - User Authentication",
-Using suggested labels:
+    description="Implement complete user authentication system",
- Type/Feature (new functionality)
+    due_on="2025-02-01T00:00:00Z"
- Priority/High (critical for auth sprint)
+)
 - Complexity/Medium (moderate architectural decisions)
 - Efforts/M (estimated 1 day)
 - Component/Backend (backend service)
 - Component/Auth (authentication system)
 - Tech/Python (Python implementation)
 - Tech/FastAPI (FastAPI framework)
 Issue created: #45
 ```
-### 5. Generate Planning Document
+Then assign issues to the milestone when creating them.
 ### 7. Generate Planning Document
 Summarize the sprint plan:
@@ -277,27 +292,24 @@ Summarize the sprint plan:
 ## Issues Created
 ### High Priority (3)
- #45: Implement JWT token generation service [Type/Feature, Component/Auth, Tech/Python]
+- #45: [Sprint 17] feat: Implement JWT token generation
- #46: Build user login endpoint [Type/Feature, Component/API, Tech/FastAPI]
+  Labels: Type/Feature, Component/Auth, Tech/Python
- #47: Create user registration form [Type/Feature, Component/Frontend, Tech/Vue]
+  Dependencies: None
-### Medium Priority (2)
+- #46: [Sprint 17] feat: Build user login endpoint
- #48: Add email verification [Type/Feature, Component/Auth]
+  Labels: Type/Feature, Component/API, Tech/FastAPI
- #49: Write authentication tests [Type/Test, Component/Testing]
+  Dependencies: #45
-## Dependencies
+- #47: [Sprint 17] feat: Create user registration form
- #45 must complete before #46
+  Labels: Type/Feature, Component/Frontend, Tech/Vue
- Database migration required before any auth work
+  Dependencies: #46
 - Frontend forms depend on API endpoints
-## Assumptions
+## Dependencies Graph
- Using existing user table schema
+#45 → #46 → #47
- Email service already configured
+       ↘ #48
 - Frontend has form validation framework
-## Open Questions
+## Milestone
- Should we support OAuth providers in this sprint?
+Sprint 17 - User Authentication (Due: 2025-02-01)
 - What's the password complexity requirement?
 ## Lessons Learned Applied
 - Sprint 12: Implementing token refresh to prevent expiration edge cases
@@ -310,149 +322,27 @@ Summarize the sprint plan:
 - `list_issues(state, labels, milestone)` - Review existing issues
 - `get_issue(number)` - Get detailed issue information
 - `create_issue(title, body, labels, assignee)` - Create new issue
 - `update_issue(number, ...)` - Update issue
 - `get_labels()` - Fetch current label taxonomy
 - `suggest_labels(context)` - Get intelligent label suggestions
 - `create_label(name, color, description)` - Create missing labels
 - `validate_repo_org()` - Check if repo is under organization
-**Wiki.js Tools:**
+**Milestone Tools:**
 - `list_milestones(state)` - List milestones
 - `create_milestone(title, description, due_on)` - Create milestone
 - `update_milestone(milestone_id, ...)` - Update milestone
 **Dependency Tools:**
 - `list_issue_dependencies(issue_number)` - List dependencies
 - `create_issue_dependency(issue_number, depends_on)` - Create dependency
 - `get_execution_order(issue_numbers)` - Get parallel execution order
 **Lessons Learned Tools (Gitea Wiki):**
 - `search_lessons(query, tags, limit)` - Search lessons learned
- `search_pages(query, tags, limit)` - Search project documentation
+- `create_lesson(title, content, tags, category)` - Create lesson
- `get_page(path)` - Fetch specific documentation page
+- `list_wiki_pages()` - List wiki pages
-
+- `get_wiki_page(page_name)` - Get wiki page content
 ## Workflow Example
 **User:** `/sprint-plan`
 > "I want to plan a sprint for extracting the Intuit Engine service from the monolith"
 **You (Planner):**
 ```
 Excellent! Let me help you plan the Intuit Engine service extraction sprint.
 First, let me check the current branch...
 [Checks git branch - confirms on development]
 ✅ Development branch confirmed. Proceeding with planning.
 Let me ask a few clarifying questions:
 1. What's the primary motivation for extracting this service?
   - Scaling independently?
   - Team ownership separation?
   - Technology stack change?
 2. Are there hard deadlines for this extraction?
 3. What's the current coupling level between Intuit Engine and the monolith?
   - Shared database?
   - Direct function calls?
   - Tight integration?
 4. Do you have a preferred approach?
   - Strangler pattern (gradual extraction)?
   - Big bang extraction?
   - API-first then extract?
 While you think about those, let me search for relevant lessons...
 [Searches lessons learned]
 search_lessons(query="service extraction", tags="architecture,refactoring", limit=10)
 📚 Found relevant lessons:
 Sprint 14: "Extracting Services Too Early"
 Key lesson: Define API contracts FIRST, write integration tests SECOND,
 then extract. Don't rush - test boundaries before extraction.
 Sprint 10: "Database Migration Gotchas"
 Key lesson: Shared database is the hardest part. Consider database-per-service
 pattern but migrate data carefully.
 These are valuable! I'll incorporate them into our plan.
 ```
 **User:** Answers the questions...
 **You (Planner):**
 ```
 Perfect, thank you! Let me analyze the architecture...
 Based on your answers and the lessons learned, here's my analysis:
 ## Architectural Approach
 Following the lesson from Sprint 14, I recommend:
 Phase 1: API Contracts & Integration Tests (Sprint 1)
 - Define clear API contracts for Intuit Engine
 - Write integration tests for these contracts
 - Validate boundaries BEFORE extraction
 Phase 2: Service Extraction (Sprint 2)
 - Extract service with tested contracts
 - Deploy as separate service
 - Gradual cutover using feature flags
 This two-sprint approach prevents the "extract then discover issues"
 problem we had before.
 ## Key Architectural Decisions
 1. **API-First Approach**
   - REST API with OpenAPI spec
   - Clear versioning strategy
   - Rationale: Prevents integration issues (Sprint 14 lesson)
 2. **Database Strategy**
   - Start with shared database
   - Plan migration to separate DB in future sprint
   - Rationale: Reduces risk, allows gradual migration (Sprint 10 lesson)
 3. **Deployment**
   - Docker container with separate scaling
   - Feature flag for gradual cutover
   - Rationale: Safe rollback if issues arise
 Now, let me create the issues...
 [Uses suggest_labels for each issue]
 Creating Issue #50: "Define Intuit Engine API Contracts"
 Labels: Type/Refactor, Priority/High, Complexity/Medium, Efforts/M,
        Component/API, Component/Backend, Tech/Python, Tech/FastAPI
 Creating Issue #51: "Write Intuit Engine Integration Tests"
 Labels: Type/Test, Priority/High, Component/Testing, Tech/Python
 Creating Issue #52: "Extract Intuit Engine Service"
 Labels: Type/Refactor, Priority/High, Complexity/Complex, Efforts/XL,
        Component/Backend, Tech/Docker, Tech/Python
 [Creates additional issues for deployment, documentation, etc.]
 ✅ Created 8 issues for Intuit Engine extraction sprint
 ## Sprint Summary
 Sprint 18 - Intuit Engine Service Extraction (Phase 1)
 **Goals:**
 - Define clear API contracts for Intuit Engine
 - Write comprehensive integration tests
 - Validate extraction boundaries before actual extraction
 **Issues Created:** 8 total (5 high priority, 3 medium)
 **Dependencies:**
 - #50 must complete before #51
 - #51 must complete before #52
 **Lessons Learned Applied:**
 - Sprint 14: API contracts first, extraction second
 - Sprint 10: Shared database initially, plan migration later
 **Estimated Effort:** 2-3 weeks
 Ready to proceed? Would you like me to adjust anything in this plan?
 ```
 ## Communication Style
@@ -476,11 +366,15 @@ Ready to proceed? Would you like me to adjust anything in this plan?
 ## Remember
-1. **Always check branch first** - No planning on production!
+1. **Never use CLI tools** - Use MCP tools exclusively for Gitea
-2. **Always search lessons learned** - Prevent repeated mistakes
+2. **Always check branch first** - No planning on production!
-3. **Always use suggest_labels** - Don't guess labels
+3. **Always validate repo is under organization** - Fail fast if not
-4. **Always ask questions** - Understand before planning
+4. **Always validate labels exist** - Create missing ones
-5. **Always think through architecture** - Consider edge cases
+5. **Always check for docs/changes/ folder** - Create if missing
-6. **Always explain decisions** - Provide rationale
+6. **Always search lessons learned** - Prevent repeated mistakes
 7. **Always use proper naming** - `[Sprint XX] <type>: <description>`
 8. **Always set up dependencies** - Use native Gitea dependencies
 9. **Always use suggest_labels** - Don't guess labels
 10. **Always think through architecture** - Consider edge cases
 You are the thoughtful planner who ensures sprints are well-prepared, architecturally sound, and learn from past experiences. Take your time, ask questions, and create comprehensive plans that set the team up for success.
--- a/plugins/projman/commands/initial-setup.md
+++ b/plugins/projman/commands/initial-setup.md
@@ -1,10 +1,10 @@
 ---
-description: Run initial setup for support-claude-mktplace
+description: Run initial setup for projman plugin
 ---
 # Initial Setup
-Run the installation script to set up the toolkit.
+Run the installation script to set up the projman plugin.
 ## What This Does
@@ -12,7 +12,9 @@ Run the installation script to set up the toolkit.
 2. Installs all dependencies
 3. Creates configuration file templates
 4. Validates existing configuration
-5. Reports remaining manual steps
+5. Validates repository organization
 6. Syncs label taxonomy
 7. Reports remaining manual steps
 ## Execution
@@ -21,13 +23,92 @@ cd ${PROJECT_ROOT}
 ./scripts/setup.sh
 ```
 ## Configuration Structure
 The plugin uses a hybrid configuration approach:
 **System-Level (credentials):**
 ```
 ~/.config/claude/gitea.env
 ```
 Contains API credentials that work across all projects.
 **Project-Level (repository/paths):**
 ```
 project-root/.env
 ```
 Contains project-specific settings like repository name.
 ## After Running
 Review the output for any manual steps required:
- Configure API credentials in `~/.config/claude/`
+
- Run `/labels-sync` to sync Gitea labels
+1. **Configure API credentials** in `~/.config/claude/gitea.env`:
- Verify Wiki.js directory structure
+   ```
   GITEA_URL=https://gitea.your-company.com
   GITEA_TOKEN=your-api-token
   GITEA_ORG=your-organization
   ```
 2. **Configure project settings** in `.env`:
   ```
   GITEA_REPO=your-repo-name
   WIKIJS_PROJECT=your-project
   ```
 3. **Run `/labels-sync`** to sync Gitea labels
 4. **Verify Gitea Wiki** is accessible and has proper structure
 ## Pre-Flight Checks
 The setup script validates:
 - Repository belongs to an organization (required)
 - Required label categories exist
 - API credentials are valid
 - Network connectivity to Gitea
 ## Re-Running
 This command is safe to run multiple times. It will skip already-completed steps.
 ## MCP Server Structure
 The plugin bundles these MCP servers:
 ```
 plugins/projman/mcp-servers/
 └── gitea/
    ├── .venv/
    ├── requirements.txt
    └── mcp_server/
        ├── server.py
        ├── gitea_client.py
        └── tools/
            ├── issues.py
            ├── labels.py
            ├── wiki.py
            ├── milestones.py
            └── dependencies.py
 ```
 ## Troubleshooting
 **Error: Repository not under organization**
 - This plugin requires repositories to belong to a Gitea organization
 - Transfer your repository to an organization or create one
 **Error: Missing required labels**
 - Run `/labels-sync` to create missing labels
 - Or create them manually in Gitea
 **Error: Cannot connect to Gitea**
 - Verify `GITEA_URL` in `~/.config/claude/gitea.env`
 - Check your API token has proper permissions
 - Ensure network connectivity
 **Error: Virtual environment creation failed**
 - Ensure Python 3.8+ is installed
 - Check disk space
 - Try running `python -m venv .venv` manually in the MCP server directory
--- a/plugins/projman/commands/labels-sync.md
+++ b/plugins/projman/commands/labels-sync.md
@@ -16,19 +16,32 @@ The label taxonomy is **dynamic** - new labels may be added to Gitea over time:
 ## What This Command Does
-1. **Fetch Current Labels** - Uses `get_labels` MCP tool to fetch all labels (org + repo)
+1. **Validate Repository** - Verify repo belongs to an organization using `validate_repo_org`
-2. **Compare with Local Reference** - Checks against `skills/label-taxonomy/labels-reference.md`
+2. **Fetch Current Labels** - Uses `get_labels` MCP tool to fetch all labels (org + repo)
-3. **Detect Changes** - Identifies new, removed, or modified labels
+3. **Compare with Local Reference** - Checks against `skills/label-taxonomy/labels-reference.md`
-4. **Explain Changes** - Shows what changed and why it matters
+4. **Detect Changes** - Identifies new, removed, or modified labels
-5. **Update Reference** - Updates the local labels-reference.md file
+5. **Explain Changes** - Shows what changed and why it matters
-6. **Confirm Update** - Asks for user confirmation before updating
+6. **Create Missing Labels** - Uses `create_label` for required labels that don't exist
 7. **Update Reference** - Updates the local labels-reference.md file
 8. **Confirm Update** - Asks for user confirmation before updating
 ## MCP Tools Used
 **Gitea Tools:**
 - `get_labels` - Fetch all labels (organization + repository)
 - `create_label` - Create missing required labels
 - `validate_repo_org` - Verify repository belongs to organization
-The command will parse the response and categorize labels by namespace and color.
+## Required Label Categories
 At minimum, these label categories must exist:
 - **Type/***: Bug, Feature, Refactor, Documentation, Test, Chore
 - **Priority/***: Low, Medium, High, Critical
 - **Complexity/***: Simple, Medium, Complex
 - **Efforts/***: XS, S, M, L, XL
 If any required labels are missing, the command will offer to create them.
 ## Expected Output
@@ -36,6 +49,10 @@ The command will parse the response and categorize labels by namespace and color
 Label Taxonomy Sync
 ===================
 Validating repository organization...
 Repository: bandit/your-repo-name
 Organization: bandit
 Fetching labels from Gitea...
 Current Label Taxonomy:
@@ -46,34 +63,36 @@ Current Label Taxonomy:
 Comparing with local reference...
 Changes Detected:
-✨ NEW: Type/Performance (org-level)
+  NEW: Type/Performance (org-level)
   Description: Performance optimization tasks
   Color: #FF6B6B
   Suggestion: Add to suggestion logic for performance-related work
-✨ NEW: Tech/Redis (repo-level)
+  NEW: Tech/Redis (repo-level)
   Description: Redis-related technology
   Color: #DC143C
   Suggestion: Add to suggestion logic for caching and data store work
-📝 MODIFIED: Priority/Critical
+  MODIFIED: Priority/Critical
   Change: Color updated from #D73A4A to #FF0000
   Impact: Visual only, no logic change needed
-❌ REMOVED: Component/Legacy
+  REMOVED: Component/Legacy
   Reason: Component deprecated and removed from codebase
   Impact: Remove from suggestion logic
 Required Labels Check:
  Type/*: 6/6 present
  Priority/*: 4/4 present
  Complexity/*: 3/3 present
  Efforts/*: 5/5 present
 Summary:
 - 2 new labels added
 - 1 label modified (color only)
 - 1 label removed
- Total labels: 44 → 45
+- Total labels: 44 -> 45
-
+- All required labels present
 Label Suggestion Logic Updates:
 - Type/Performance: Suggest for keywords "optimize", "performance", "slow", "speed"
 - Tech/Redis: Suggest for keywords "cache", "redis", "session", "pubsub"
 - Component/Legacy: Remove from all suggestion contexts
 Update local reference file?
 [Y/n]
@@ -135,9 +154,9 @@ Source: Gitea (bandit/your-repo-name)
 When suggesting labels, consider:
 **Type Detection:**
- Keywords "bug", "fix", "error" → Type/Bug
+- Keywords "bug", "fix", "error" -> Type/Bug
- Keywords "feature", "add", "implement" → Type/Feature
+- Keywords "feature", "add", "implement" -> Type/Feature
- Keywords "refactor", "extract", "restructure" → Type/Refactor
+- Keywords "refactor", "extract", "restructure" -> Type/Refactor
 ...
 ```
@@ -161,6 +180,9 @@ The updated taxonomy is used by:
 ```
 User: /labels-sync
 Validating repository organization...
 Repository: bandit/your-repo-name
 Fetching labels from Gitea...
 Current Label Taxonomy:
@@ -170,26 +192,43 @@ Current Label Taxonomy:
 Comparing with local reference...
-✅ No changes detected. Label taxonomy is up to date.
+No changes detected. Label taxonomy is up to date.
 Last synced: 2025-01-18 14:30 UTC
 ```
 ```
 User: /labels-sync
 Fetching labels from Gitea...
 Changes Detected:
-✨ NEW: Type/Performance
+  NEW: Type/Performance
-✨ NEW: Tech/Redis
+  NEW: Tech/Redis
 Required Labels Check:
  MISSING: Complexity/Simple
  MISSING: Complexity/Medium
  MISSING: Complexity/Complex
 Would you like me to create the missing required labels? [Y/n] y
 Creating missing labels...
  Created: Complexity/Simple
  Created: Complexity/Medium
  Created: Complexity/Complex
 Update local reference file? [Y/n] y
-✅ Label taxonomy updated successfully!
+Label taxonomy updated successfully!
-✅ Suggestion logic updated with new labels
+Suggestion logic updated with new labels
 New labels available for use:
 - Type/Performance
 - Tech/Redis
 - Complexity/Simple
 - Complexity/Medium
 - Complexity/Complex
 ```
 ## Troubleshooting
@@ -199,6 +238,10 @@ New labels available for use:
 - Verify your API token has `read:org` and `repo` permissions
 - Ensure you're connected to the network
 **Error: Repository is not under an organization**
 - This plugin requires repositories to belong to an organization
 - Transfer the repository to an organization or create one
 **Error: Permission denied to update reference file**
 - Check file permissions on `skills/label-taxonomy/labels-reference.md`
 - Ensure you have write access to the plugin directory
@@ -210,8 +253,8 @@ New labels available for use:
 ## Best Practices
-1. **Sync regularly** - Run monthly or when notified of label changes
+1. **Sync at sprint start** - Ensure labels are current before planning
 2. **Review changes** - Always review what changed before confirming
-3. **Update planning** - After sync, consider if new labels affect current sprint
+3. **Create missing required labels** - Don't skip this step
-4. **Communicate changes** - Let team know when new labels are available
+4. **Update planning** - After sync, consider if new labels affect current sprint
-5. **Keep skill updated** - The label-taxonomy skill should match the reference file
+5. **Communicate changes** - Let team know when new labels are available
--- a/plugins/projman/commands/sprint-close.md
+++ b/plugins/projman/commands/sprint-close.md
@@ -1,10 +1,10 @@
 ---
-description: Complete sprint and capture lessons learned to Wiki.js
+description: Complete sprint and capture lessons learned to Gitea Wiki
 ---
 # Close Sprint and Capture Lessons Learned
-This command completes the sprint and captures lessons learned to Wiki.js. **This is critical** - after 15 sprints without lesson capture, repeated mistakes occurred (e.g., Claude Code infinite loops 2-3 times on similar issues).
+This command completes the sprint and captures lessons learned to Gitea Wiki. **This is critical** - after 15 sprints without lesson capture, repeated mistakes occurred (e.g., Claude Code infinite loops 2-3 times on similar issues).
 ## Why Lessons Learned Matter
@@ -20,7 +20,8 @@ This command completes the sprint and captures lessons learned to Wiki.js. **Thi
 The orchestrator agent will guide you through:
 1. **Review Sprint Completion**
-   - Verify all issues are closed or moved to backlog
+   - Use `list_issues` to verify all issues are closed or moved to backlog
   - Check milestone completion status
   - Check for incomplete work needing carryover
   - Review overall sprint goals vs. actual completion
@@ -35,10 +36,9 @@ The orchestrator agent will guide you through:
   - Ensure future sprints can find these lessons via search
   - Use consistent tagging for patterns
-4. **Update Wiki.js**
+4. **Save to Gitea Wiki**
-   - Use `create_lesson` to save lessons to Wiki.js
+   - Use `create_lesson` to save lessons to Gitea Wiki
-   - Create lessons in `/projects/{project}/lessons-learned/sprints/`
+   - Create lessons in project wiki under `lessons-learned/sprints/`
   - Update INDEX.md automatically
   - Make lessons searchable for future sprints
 5. **Git Operations**
@@ -47,6 +47,10 @@ The orchestrator agent will guide you through:
   - Clean up merged branches
   - Tag sprint completion
 6. **Close Milestone**
   - Use `update_milestone` to close the sprint milestone
   - Document final completion status
 ## MCP Tools Available
 **Gitea Tools:**
@@ -54,11 +58,15 @@ The orchestrator agent will guide you through:
 - `get_issue` - Get detailed issue information for retrospective
 - `update_issue` - Move incomplete issues to next sprint
-**Wiki.js Tools:**
+**Milestone Tools:**
 - `get_milestone` - Get milestone status
 - `update_milestone` - Close milestone
 **Lessons Learned Tools (Gitea Wiki):**
 - `create_lesson` - Create lessons learned entry
- `tag_lesson` - Add/update tags on lessons
+- `search_lessons` - Check for similar existing lessons
- `list_pages` - Check existing lessons learned
+- `list_wiki_pages` - Check existing lessons learned
- `update_page` - Update INDEX.md if needed
+- `get_wiki_page` - Read existing lessons
 ## Lesson Structure
@@ -165,8 +173,9 @@ The orchestrator agent will:
 2. Identify preventable mistakes vs. expected challenges
 3. Structure lessons in the proper format
 4. Suggest appropriate tags
-5. Create lessons in Wiki.js using `create_lesson`
+5. Create lessons in Gitea Wiki using `create_lesson`
 6. Ensure lessons are discoverable for future sprints
 7. Handle git operations and milestone closure
 ## Example Sprint Close Session
@@ -178,14 +187,14 @@ First, let me review the sprint completion...
 [Uses list_issues to check sprint status]
-Sprint 16 Summary:
+Sprint 18 Summary:
 - 8 issues planned
 - 7 completed (87.5%)
 - 1 moved to backlog (#52: Deploy auth service - blocked by infra)
 Great progress! Now, let's capture lessons learned.
-What went wrong or what challenges did you face this sprint?
+What challenges did you face this sprint?
 User: Claude Code got stuck in a loop when pytest validation tests failed
@@ -200,10 +209,10 @@ Let me ask some clarifying questions:
 I'll create this lesson with tags: testing, claude-code, validation, python, pytest, debugging
-[Uses create_lesson to save to Wiki.js]
+[Uses create_lesson to save to Gitea Wiki]
-Lesson created: "Sprint 16 - Claude Code Infinite Loop on Validation Errors"
+Lesson created: "Sprint 18 - Claude Code Infinite Loop on Validation Errors"
-Path: /projects/cuisineflow/lessons-learned/sprints/sprint-16-validation-loop.md
+Saved to Gitea Wiki with appropriate tags.
 Any other lessons from this sprint?
@@ -215,7 +224,14 @@ Orchestrator: Excellent - let's capture that too...
 All lessons captured! They'll be searchable when planning future sprints.
-Would you like me to handle git operations (merge branches, tag release)?
+Would you like me to handle git operations?
 - Commit any remaining changes
 - Merge feature branches to development
 - Tag sprint completion (v0.18.0)
 - Clean up merged branches
 - Close milestone
 [Y/n]
 ```
 ## Getting Started
@@ -223,7 +239,8 @@ Would you like me to handle git operations (merge branches, tag release)?
 Simply run `/sprint-close` when your sprint is complete. The orchestrator will guide you through:
 1. Sprint review
 2. Lessons learned capture
-3. Wiki.js updates
+3. Gitea Wiki updates
 4. Git operations
 5. Milestone closure
 **Don't skip this step!** Future sprints will thank you for capturing these insights.
--- a/plugins/projman/commands/sprint-plan.md
+++ b/plugins/projman/commands/sprint-plan.md
@@ -6,21 +6,57 @@ description: Start sprint planning with AI-guided architecture analysis and issu
 You are initiating sprint planning. The planner agent will guide you through architecture analysis, ask clarifying questions, and help create well-structured Gitea issues with appropriate labels.
-## Branch Detection
+## CRITICAL: Pre-Planning Validations
-**CRITICAL:** Before proceeding, check the current git branch:
+**BEFORE PLANNING**, the planner agent performs mandatory checks:
 ### 1. Branch Detection
 ```bash
 git branch --show-current
 ```
 **Branch Requirements:**
- ✅ **Development branches** (`development`, `develop`, `feat/*`, `dev/*`): Full planning capabilities
+- **Development branches** (`development`, `develop`, `feat/*`, `dev/*`): Full planning capabilities
- ⚠️ **Staging branches** (`staging`, `stage/*`): Can create issues to document needed changes, but cannot modify code
+- **Staging branches** (`staging`, `stage/*`): Can create issues to document needed changes, but cannot modify code
- ❌ **Production branches** (`main`, `master`, `prod/*`): READ-ONLY - no planning allowed
+- **Production branches** (`main`, `master`, `prod/*`): READ-ONLY - no planning allowed
 If you are on a production or staging branch, you MUST stop and ask the user to switch to a development branch.
 ### 2. Repository Organization Check
 Use `validate_repo_org` MCP tool to verify the repository belongs to an organization.
 **If NOT an organization repository:**
 ```
 REPOSITORY VALIDATION FAILED
 This plugin requires the repository to belong to an organization, not a user.
 Please transfer or create the repository under that organization.
 ```
 ### 3. Label Taxonomy Validation
 Verify all required labels exist using `get_labels`:
 **Required label categories:**
 - Type/* (Bug, Feature, Refactor, Documentation, Test, Chore)
 - Priority/* (Low, Medium, High, Critical)
 - Complexity/* (Simple, Medium, Complex)
 - Efforts/* (XS, S, M, L, XL)
 **If labels are missing:** Use `create_label` to create them.
 ### 4. docs/changes/ Folder Check
 Verify the project has a `docs/changes/` folder for sprint input files.
 **If folder does NOT exist:** Prompt user to create it.
 **If sprint starts with discussion but no input file:**
 - Capture the discussion outputs
 - Create a change file: `docs/changes/sprint-XX-description.md`
 ## Planning Workflow
 The planner agent will:
@@ -44,27 +80,78 @@ The planner agent will:
 4. **Create Gitea Issues**
   - Use the `create_issue` MCP tool for each planned task
   - Apply appropriate labels using `suggest_labels` tool
-   - Structure issues with clear titles and descriptions
+   - **Issue Title Format (MANDATORY):** `[Sprint XX] <type>: <description>`
   - Include acceptance criteria and technical notes
-5. **Generate Planning Document**
+5. **Set Up Dependencies**
   - Use `create_issue_dependency` to establish task dependencies
   - This enables parallel execution planning
 6. **Create or Select Milestone**
   - Use `create_milestone` to group sprint issues
   - Assign issues to the milestone
 7. **Generate Planning Document**
   - Summarize architectural decisions
   - List created issues with labels
-   - Document assumptions and open questions
+   - Document dependency graph
   - Provide sprint overview
 ## Issue Title Format (MANDATORY)
 ```
 [Sprint XX] <type>: <description>
 ```
 **Types:**
 - `feat` - New feature
 - `fix` - Bug fix
 - `refactor` - Code refactoring
 - `docs` - Documentation
 - `test` - Test additions/changes
 - `chore` - Maintenance tasks
 **Examples:**
 - `[Sprint 17] feat: Add user email validation`
 - `[Sprint 17] fix: Resolve login timeout issue`
 - `[Sprint 18] refactor: Extract authentication module`
 ## Task Granularity Guidelines
 | Size | Scope | Example |
 |------|-------|---------|
 | **Small** | 1-2 hours, single file/component | Add validation to one field |
 | **Medium** | Half day, multiple files, one feature | Implement new API endpoint |
 | **Large** | Should be broken down | Full authentication system |
 **If a task is too large, break it down into smaller tasks.**
 ## MCP Tools Available
 **Gitea Tools:**
 - `list_issues` - Review existing issues
 - `get_issue` - Get detailed issue information
 - `create_issue` - Create new issue with labels
 - `update_issue` - Update issue
 - `get_labels` - Fetch current label taxonomy
 - `suggest_labels` - Get intelligent label suggestions based on context
- `create_issue` - Create new issue with labels
+- `create_label` - Create missing labels
 - `validate_repo_org` - Check if repo is under organization
-**Wiki.js Tools:**
+**Milestone Tools:**
 - `list_milestones` - List milestones
 - `create_milestone` - Create milestone
 - `update_milestone` - Update milestone
 **Dependency Tools:**
 - `create_issue_dependency` - Create dependency between issues
 - `list_issue_dependencies` - List dependencies for an issue
 - `get_execution_order` - Get parallel execution batches
 **Lessons Learned Tools (Gitea Wiki):**
 - `search_lessons` - Search lessons learned from previous sprints
- `search_pages` - Search project documentation
+- `list_wiki_pages` - List wiki pages
- `get_page` - Fetch specific documentation page
+- `get_wiki_page` - Fetch specific documentation page
 ## Label Taxonomy
@@ -92,7 +179,11 @@ The planner agent is thoughtful and methodical:
 ```
 User: I want to plan a sprint for user authentication
-Planner: Great! Let me ask a few questions to understand the scope:
+Planner: Great! Let me first run pre-planning validations...
 [Checks branch, repo org, labels, docs/changes folder]
 All validations passed. Now let me ask a few questions:
 1. What authentication method are you planning? (JWT, OAuth, session-based?)
 2. Are there any specific security requirements or compliance needs?
@@ -109,12 +200,28 @@ Based on previous experience, I found these relevant lessons:
 Now, let me analyze the architecture...
-[Creates issues with appropriate labels]
+[Creates issues with appropriate labels and dependencies]
 Created 5 issues for the authentication sprint:
- Issue #45: Implement JWT token generation [Type/Feature, Priority/High, Component/Auth, Tech/Python]
+- Issue #45: [Sprint 17] feat: Implement JWT token generation
- Issue #46: Build user login endpoint [Type/Feature, Priority/High, Component/API, Tech/FastAPI]
+  Labels: Type/Feature, Priority/High, Component/Auth, Tech/Python
-...
+  Dependencies: None
 - Issue #46: [Sprint 17] feat: Build user login endpoint
  Labels: Type/Feature, Priority/High, Component/API, Tech/FastAPI
  Dependencies: #45
 - Issue #47: [Sprint 17] feat: Create user registration form
  Labels: Type/Feature, Priority/Medium, Component/Frontend, Tech/Vue
  Dependencies: #46
 Dependency Graph:
 #45 -> #46 -> #47
       |
       v
      #48
 Milestone: Sprint 17 - User Authentication (Due: 2025-02-01)
 ```
 ## Getting Started
@@ -124,4 +231,11 @@ Invoke the planner agent by providing your sprint goals. The agent will guide yo
 **Example:**
 > "I want to plan a sprint for extracting the Intuit Engine service from the monolith"
-The planner will then ask clarifying questions and guide you through the complete planning workflow.
+The planner will then:
 1. Run pre-planning validations
 2. Ask clarifying questions
 3. Search lessons learned
 4. Create issues with proper naming and labels
 5. Set up dependencies
 6. Create milestone
 7. Generate planning summary
--- a/plugins/projman/commands/sprint-start.md
+++ b/plugins/projman/commands/sprint-start.md
@@ -4,7 +4,7 @@ description: Begin sprint execution with relevant lessons learned from previous
 # Start Sprint Execution
-You are initiating sprint execution. The orchestrator agent will coordinate the work, search for relevant lessons learned, and guide you through the implementation process.
+You are initiating sprint execution. The orchestrator agent will coordinate the work, analyze dependencies for parallel execution, search for relevant lessons learned, and guide you through the implementation process.
 ## Branch Detection
@@ -15,9 +15,9 @@ git branch --show-current
 ```
 **Branch Requirements:**
- ✅ **Development branches** (`development`, `develop`, `feat/*`, `dev/*`): Full execution capabilities
+- **Development branches** (`development`, `develop`, `feat/*`, `dev/*`): Full execution capabilities
- ⚠️ **Staging branches** (`staging`, `stage/*`): Can create issues to document bugs, but cannot modify code
+- **Staging branches** (`staging`, `stage/*`): Can create issues to document bugs, but cannot modify code
- ❌ **Production branches** (`main`, `master`, `prod/*`): READ-ONLY - no execution allowed
+- **Production branches** (`main`, `master`, `prod/*`): READ-ONLY - no execution allowed
 If you are on a production or staging branch, you MUST stop and ask the user to switch to a development branch.
@@ -25,32 +25,72 @@ If you are on a production or staging branch, you MUST stop and ask the user to
 The orchestrator agent will:
-1. **Review Sprint Issues**
+1. **Fetch Sprint Issues**
   - Use `list_issues` to fetch open issues for the sprint
   - Identify priorities based on labels (Priority/Critical, Priority/High, etc.)
   - Understand dependencies between issues
-2. **Search Relevant Lessons Learned**
+2. **Analyze Dependencies and Plan Parallel Execution**
   - Use `get_execution_order` to build dependency graph
   - Identify batches that can be executed in parallel
   - Present parallel execution plan
 3. **Search Relevant Lessons Learned**
   - Use `search_lessons` to find experiences from past sprints
   - Search by tags matching the current sprint's technology and components
   - Review patterns, gotchas, and preventable mistakes
   - Present relevant lessons before starting work
-3. **Identify Next Task**
+4. **Dispatch Tasks (Parallel When Possible)**
-   - Select the highest priority task that's unblocked
+   - For independent tasks (same batch), spawn multiple Executor agents in parallel
-   - Review task details and acceptance criteria
+   - For dependent tasks, execute sequentially
-   - Check for dependencies
+   - Create proper branch for each task
 4. **Generate Lean Execution Prompt**
   - Create concise implementation guidance (NOT full planning docs)
   - Reference architectural decisions from planning phase
   - Highlight relevant lessons learned
   - Provide clear acceptance criteria
 5. **Track Progress**
   - Update issue status as work progresses
   - Use `add_comment` to document progress and blockers
-   - Identify when tasks are blocked and need attention
+   - Monitor when dependencies are satisfied and new tasks become unblocked
 ## Parallel Execution Model
 The orchestrator analyzes dependencies and groups issues into parallelizable batches:
 ```
 Parallel Execution Batches:
 +---------------------------------------------------------------+
 | Batch 1 (can start immediately):                               |
 |   #45 [Sprint 18] feat: Implement JWT service                  |
 |   #48 [Sprint 18] docs: Update API documentation               |
 +---------------------------------------------------------------+
 | Batch 2 (after batch 1):                                       |
 |   #46 [Sprint 18] feat: Build login endpoint (needs #45)       |
 |   #49 [Sprint 18] test: Add auth tests (needs #45)             |
 +---------------------------------------------------------------+
 | Batch 3 (after batch 2):                                       |
 |   #47 [Sprint 18] feat: Create login form (needs #46)          |
 +---------------------------------------------------------------+
 ```
 **Independent tasks in the same batch run in parallel.**
 ## Branch Naming Convention (MANDATORY)
 When creating branches for tasks:
 - Features: `feat/<issue-number>-<short-description>`
 - Bug fixes: `fix/<issue-number>-<short-description>`
 - Debugging: `debug/<issue-number>-<short-description>`
 **Examples:**
 ```bash
 git checkout -b feat/45-jwt-service
 git checkout -b fix/46-login-timeout
 git checkout -b debug/47-investigate-memory-leak
 ```
 **Validation:**
 - Issue number MUST be present
 - Prefix MUST be `feat/`, `fix/`, or `debug/`
 - Description should be kebab-case (lowercase, hyphens)
 ## MCP Tools Available
@@ -60,34 +100,54 @@ The orchestrator agent will:
 - `update_issue` - Update issue status, assignee, labels
 - `add_comment` - Add progress updates or blocker notes
-**Wiki.js Tools:**
+**Dependency Tools:**
 - `list_issue_dependencies` - Get dependencies for an issue
 - `get_execution_order` - Get parallel execution batches for sprint issues
 **Milestone Tools:**
 - `list_milestones` - List milestones
 - `get_milestone` - Get milestone details
 **Lessons Learned Tools (Gitea Wiki):**
 - `search_lessons` - Find relevant lessons from past sprints
- `search_pages` - Search project documentation for references
+- `list_wiki_pages` - List project documentation
- `get_page` - Fetch specific documentation (e.g., architecture decisions)
+- `get_wiki_page` - Fetch specific documentation (e.g., architecture decisions)
 ## Orchestrator Personality
 The orchestrator agent is concise and action-oriented:
 - Generates lean execution prompts, not lengthy documents
 - Tracks details meticulously (no task forgotten)
 - Coordinates parallel execution based on dependencies
 - Identifies blockers proactively
 - Coordinates Git operations (commit, merge, cleanup)
 - Manages task dependencies
 - Updates documentation as work progresses
 ## Example Sprint Start Session
 ```
 User: /sprint-start
-Orchestrator: Starting sprint execution. Let me review open issues and relevant lessons...
+Orchestrator: Starting sprint execution. Let me analyze the sprint...
 [Uses list_issues to fetch sprint backlog]
-Found 8 open issues for this sprint:
+Found 5 open issues for this sprint.
- Issue #45: Implement JWT token generation [Priority/High, Component/Auth]
+
- Issue #46: Build user login endpoint [Priority/High, Component/API]
+[Uses get_execution_order to analyze dependencies]
- Issue #47: Create user registration form [Priority/Medium, Component/Frontend]
+
-...
+Parallel Execution Batches:
 +-----------------------------------------------+
 | Batch 1 (can start immediately):               |
 |   #45 - Implement JWT service                  |
 |   #48 - Update API documentation               |
 +-----------------------------------------------+
 | Batch 2 (after batch 1):                       |
 |   #46 - Build login endpoint (needs #45)       |
 |   #49 - Add auth tests (needs #45)             |
 +-----------------------------------------------+
 | Batch 3 (after batch 2):                       |
 |   #47 - Create login form (needs #46)          |
 +-----------------------------------------------+
 [Uses search_lessons to find relevant past experiences]
@@ -95,38 +155,53 @@ Relevant lessons learned:
 - Sprint 12: "JWT Token Expiration Edge Cases" - Remember to handle token refresh
 - Sprint 8: "OAuth Integration Pitfalls" - Test error handling for auth providers
-[Identifies next task based on priority and dependencies]
+Ready to start? I can dispatch multiple tasks in parallel.
-Next task: Issue #45 - Implement JWT token generation
+Dispatching Batch 1 (2 tasks in parallel):
 This is unblocked and high priority.
-Execution prompt:
+Task 1: #45 - Implement JWT service
- Create JWT token generation utility in backend/auth/jwt.py
+  Branch: feat/45-jwt-service
- Use HS256 algorithm with secret from environment variable
+  Executor: Starting...
 - Include user_id, email, and expiration in payload
 - Add token refresh logic (remember lesson from Sprint 12!)
 - Write unit tests for token generation and validation
-Would you like me to invoke the executor agent for implementation guidance?
+Task 2: #48 - Update API documentation
  Branch: feat/48-api-docs
  Executor: Starting...
 Both tasks running in parallel. I'll monitor progress.
 ```
-## Lessons Learned Integration
+## Lean Execution Prompts
-The orchestrator actively searches for and presents relevant lessons before starting work:
+The orchestrator generates concise prompts (NOT verbose documents):
 **Search by Technology:**
 ```
 search_lessons(tags="python,fastapi,jwt")
 ```
 Next Task: #45 - [Sprint 18] feat: Implement JWT token generation
-**Search by Component:**
+Priority: High | Effort: M (1 day) | Unblocked
-```
+Branch: feat/45-jwt-service
 search_lessons(tags="authentication,api,backend")
 ```
-**Search by Keywords:**
+Quick Context:
-```
+- Create backend service for JWT tokens
-search_lessons(query="token expiration edge cases")
+- Use HS256 algorithm (decision from planning)
 - Include user_id, email, expiration in payload
 Key Actions:
 1. Create auth/jwt_service.py
 2. Implement generate_token(user_id, email)
 3. Implement verify_token(token)
 4. Add token refresh logic (Sprint 12 lesson!)
 5. Write unit tests for generation/validation
 Acceptance Criteria:
 - Tokens generate successfully
 - Token verification works
 - Refresh prevents expiration issues
 - Tests cover edge cases
 Relevant Lessons:
 Sprint 12: Handle token refresh explicitly to prevent mid-request expiration
 Dependencies: None (can start immediately)
 ```
 ## Progress Tracking
@@ -145,16 +220,32 @@ update_issue(issue_number=45, state="closed")
 **Document Blockers:**
 ```
-add_comment(issue_number=46, body="Blocked: Waiting for auth database schema migration")
+add_comment(issue_number=46, body="BLOCKED: Waiting for #45 to complete (dependency)")
 ```
 **Track Parallel Execution:**
 ```
 Parallel Execution Status:
 Batch 1:
  #45 - JWT service - COMPLETED (12:45)
  #48 - API docs - IN PROGRESS (75%)
 Batch 2 (now unblocked):
  #46 - Login endpoint - READY TO START
  #49 - Auth tests - READY TO START
 #45 completed! #46 and #49 are now unblocked.
 Starting #46 while #48 continues...
 ```
 ## Getting Started
 Simply invoke `/sprint-start` and the orchestrator will:
 1. Review your sprint backlog
-2. Search for relevant lessons
+2. Analyze dependencies and plan parallel execution
-3. Identify the next task to work on
+3. Search for relevant lessons
-4. Provide lean execution guidance
+4. Dispatch tasks (parallel when possible)
 5. Track progress as you work
-The orchestrator keeps you focused and ensures nothing is forgotten.
+The orchestrator keeps you focused, maximizes parallelism, and ensures nothing is forgotten.
--- a/plugins/projman/commands/sprint-status.md
+++ b/plugins/projman/commands/sprint-status.md
@@ -4,15 +4,16 @@ description: Check current sprint progress and identify blockers
 # Sprint Status Check
-This command provides a quick overview of your current sprint progress, including open issues, completed work, and potential blockers.
+This command provides a quick overview of your current sprint progress, including open issues, completed work, dependency status, and potential blockers.
 ## What This Command Does
 1. **Fetch Sprint Issues** - Lists all issues with current sprint labels/milestone
-2. **Categorize by Status** - Groups issues into: Open, In Progress, Blocked, Completed
+2. **Analyze Dependencies** - Shows dependency graph and blocked/unblocked tasks
-3. **Identify Blockers** - Highlights issues with blocker comments or dependencies
+3. **Categorize by Status** - Groups issues into: Open, In Progress, Blocked, Completed
-4. **Show Progress Summary** - Provides completion percentage and velocity insights
+4. **Identify Blockers** - Highlights issues with blocker comments or unmet dependencies
-5. **Highlight Priorities** - Shows critical and high-priority items needing attention
+5. **Show Progress Summary** - Provides completion percentage and parallel execution status
 6. **Highlight Priorities** - Shows critical and high-priority items needing attention
 ## Usage
@@ -22,53 +23,98 @@ Simply run `/sprint-status` to get a comprehensive sprint overview.
 This command uses the following Gitea MCP tools:
 **Issue Tools:**
 - `list_issues(state="open")` - Fetch open issues
 - `list_issues(state="closed")` - Fetch completed issues
 - `get_issue(number)` - Get detailed issue information for blockers
 **Dependency Tools:**
 - `list_issue_dependencies(issue_number)` - Get dependencies for each issue
 - `get_execution_order(issue_numbers)` - Get parallel execution batches
 **Milestone Tools:**
 - `get_milestone(milestone_id)` - Get milestone progress
 ## Expected Output
 ```
 Sprint Status Report
 ====================
-Sprint: Sprint 16 - Authentication System
+Sprint: Sprint 18 - Authentication System
 Milestone: Due 2025-02-01 (5 days remaining)
 Date: 2025-01-18
 Progress Summary:
 - Total Issues: 8
 - Completed: 3 (37.5%)
 - In Progress: 2 (25%)
- Open: 2 (25%)
+- Ready: 2 (25%)
 - Blocked: 1 (12.5%)
 Dependency Graph:
 #45 -> #46 -> #47
  |
  v
 #49 -> #50
 Parallel Execution Status:
 +-----------------------------------------------+
 | Batch 1 (COMPLETED):                           |
 |   #45 - Implement JWT service                  |
 |   #48 - Update API documentation               |
 +-----------------------------------------------+
 | Batch 2 (IN PROGRESS):                         |
 |   #46 - Build login endpoint (75%)             |
 |   #49 - Add auth tests (50%)                   |
 +-----------------------------------------------+
 | Batch 3 (BLOCKED):                             |
 |   #47 - Create login form (waiting for #46)    |
 +-----------------------------------------------+
 Completed Issues (3):
-✅ #45: Implement JWT token generation [Type/Feature, Priority/High]
+  #45: [Sprint 18] feat: Implement JWT service [Type/Feature, Priority/High]
-✅ #46: Build user login endpoint [Type/Feature, Priority/High]
+  #48: [Sprint 18] docs: Update API documentation [Type/Docs, Priority/Medium]
-✅ #48: Write authentication tests [Type/Test, Priority/Medium]
+  #51: [Sprint 18] chore: Update dependencies [Type/Chore, Priority/Low]
 In Progress (2):
-🔄 #47: Create user registration form [Type/Feature, Priority/Medium]
+  #46: [Sprint 18] feat: Build login endpoint [Type/Feature, Priority/High]
-🔄 #49: Add password reset flow [Type/Feature, Priority/Low]
+  #49: [Sprint 18] test: Add auth tests [Type/Test, Priority/Medium]
-Open Issues (2):
+Ready to Start (2):
-📋 #50: Integrate OAuth providers [Type/Feature, Priority/Low]
+  #50: [Sprint 18] feat: Integrate OAuth providers [Type/Feature, Priority/Low]
-📋 #51: Add email verification [Type/Feature, Priority/Medium]
+  #52: [Sprint 18] feat: Add email verification [Type/Feature, Priority/Medium]
 Blocked Issues (1):
-🚫 #52: Deploy auth service [Type/Deploy, Priority/High]
+  #47: [Sprint 18] feat: Create login form [Type/Feature, Priority/High]
-   Blocker: Waiting for database migration approval
+     Blocked by: #46 (in progress)
 Priority Alerts:
-⚠️  1 high-priority item blocked: #52
+  1 high-priority item blocked: #47
-✅ All critical items completed
+  All critical items completed
 Recommendations:
-1. Focus on unblocking #52 (Deploy auth service)
+1. Focus on completing #46 (Login endpoint) - unblocks #47
-2. Continue work on #47 (User registration form)
+2. Continue parallel work on #49 (Auth tests)
-3. Consider starting #51 (Email verification) next
+3. #50 and #52 are ready - can start in parallel
 ```
 ## Dependency Analysis
 The status check analyzes dependencies to show:
 **Blocked Issues:**
 - Issues waiting for other issues to complete
 - Shows which issue is blocking and its current status
 **Unblocked Issues:**
 - Issues with no pending dependencies
 - Ready to be picked up immediately
 **Parallel Opportunities:**
 - Multiple unblocked issues that can run simultaneously
 - Maximizes sprint velocity
 ## Filtering Options
 You can optionally filter the status check:
@@ -82,7 +128,7 @@ list_issues(labels=["Priority/High"])
 **By Milestone:**
 ```
 Show issues for specific sprint:
-list_issues(milestone="Sprint 16")
+list_issues(milestone="Sprint 18")
 ```
 **By Component:**
@@ -94,9 +140,9 @@ list_issues(labels=["Component/Backend"])
 ## Blocker Detection
 The command identifies blocked issues by:
-1. Checking issue comments for keywords: "blocked", "blocker", "waiting for", "dependency"
+1. **Dependency Analysis** - Uses `list_issue_dependencies` to find unmet dependencies
-2. Looking for issues with no recent activity (>7 days)
+2. **Comment Keywords** - Checks for "blocked", "blocker", "waiting for"
-3. Identifying issues with unresolved dependencies
+3. **Stale Issues** - Issues with no recent activity (>7 days)
 ## When to Use
@@ -106,6 +152,7 @@ Run `/sprint-status` when you want to:
 - Check if the sprint is on track
 - Identify bottlenecks or blockers
 - Decide what to work on next
 - See which tasks can run in parallel
 ## Integration with Other Commands
@@ -116,4 +163,17 @@ Run `/sprint-status` when you want to:
 ## Example Usage
 ```
-User: /sprint-status
+User: /sprint-status
 Sprint Status Report
 ====================
 Sprint: Sprint 18 - Authentication System
 Progress: 3/8 (37.5%)
 Next Actions:
 1. Complete #46 - it's blocking #47
 2. Start #50 or #52 - both are unblocked
 Would you like me to generate execution prompts for the unblocked tasks?
 ```
--- a/plugins/projman/mcp-servers/gitea/mcp_server/gitea_client.py
+++ b/plugins/projman/mcp-servers/gitea/mcp_server/gitea_client.py
@@ -6,9 +6,13 @@ Provides synchronous methods for:
 - Label management
 - Repository operations
 - PMO multi-repo aggregation
 - Wiki operations (lessons learned)
 - Milestone management
 - Issue dependencies
 """
 import requests
 import logging
 import re
 from typing import List, Dict, Optional
 from .config import GiteaConfig
@@ -209,3 +213,381 @@ class GiteaClient:
                logger.error(f"Error fetching issues from {repo_name}: {e}")
        return aggregated
    # ========================================
    # WIKI OPERATIONS (Lessons Learned)
    # ========================================
    def list_wiki_pages(self, repo: Optional[str] = None) -> List[Dict]:
        """List all wiki pages in repository."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/wiki/pages"
        logger.info(f"Listing wiki pages from {owner}/{target_repo}")
        response = self.session.get(url)
        response.raise_for_status()
        return response.json()
    def get_wiki_page(
        self,
        page_name: str,
        repo: Optional[str] = None
    ) -> Dict:
        """Get a specific wiki page by name."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/wiki/page/{page_name}"
        logger.info(f"Getting wiki page '{page_name}' from {owner}/{target_repo}")
        response = self.session.get(url)
        response.raise_for_status()
        return response.json()
    def create_wiki_page(
        self,
        title: str,
        content: str,
        repo: Optional[str] = None
    ) -> Dict:
        """Create a new wiki page."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/wiki/new"
        data = {
            'title': title,
            'content_base64': self._encode_base64(content)
        }
        logger.info(f"Creating wiki page '{title}' in {owner}/{target_repo}")
        response = self.session.post(url, json=data)
        response.raise_for_status()
        return response.json()
    def update_wiki_page(
        self,
        page_name: str,
        content: str,
        repo: Optional[str] = None
    ) -> Dict:
        """Update an existing wiki page."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/wiki/page/{page_name}"
        data = {
            'content_base64': self._encode_base64(content)
        }
        logger.info(f"Updating wiki page '{page_name}' in {owner}/{target_repo}")
        response = self.session.patch(url, json=data)
        response.raise_for_status()
        return response.json()
    def delete_wiki_page(
        self,
        page_name: str,
        repo: Optional[str] = None
    ) -> bool:
        """Delete a wiki page."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/wiki/page/{page_name}"
        logger.info(f"Deleting wiki page '{page_name}' from {owner}/{target_repo}")
        response = self.session.delete(url)
        response.raise_for_status()
        return True
    def _encode_base64(self, content: str) -> str:
        """Encode content to base64 for wiki API."""
        import base64
        return base64.b64encode(content.encode('utf-8')).decode('utf-8')
    def _decode_base64(self, content: str) -> str:
        """Decode base64 content from wiki API."""
        import base64
        return base64.b64decode(content.encode('utf-8')).decode('utf-8')
    def search_wiki_pages(
        self,
        query: str,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """Search wiki pages by content (client-side filtering)."""
        pages = self.list_wiki_pages(repo)
        results = []
        query_lower = query.lower()
        for page in pages:
            if query_lower in page.get('title', '').lower():
                results.append(page)
        return results
    def create_lesson(
        self,
        title: str,
        content: str,
        tags: List[str],
        category: str = "sprints",
        repo: Optional[str] = None
    ) -> Dict:
        """Create a lessons learned entry in the wiki."""
        # Sanitize title for wiki page name
        page_name = f"lessons/{category}/{self._sanitize_page_name(title)}"
        # Add tags as metadata at the end of content
        full_content = f"{content}\n\n---\n**Tags:** {', '.join(tags)}"
        return self.create_wiki_page(page_name, full_content, repo)
    def search_lessons(
        self,
        query: Optional[str] = None,
        tags: Optional[List[str]] = None,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """Search lessons learned by query and/or tags."""
        pages = self.list_wiki_pages(repo)
        results = []
        for page in pages:
            title = page.get('title', '')
            # Filter to only lessons (pages starting with lessons/)
            if not title.startswith('lessons/'):
                continue
            # If query provided, check if it matches title
            if query:
                if query.lower() not in title.lower():
                    continue
            # Get full page content for tag matching if tags provided
            if tags:
                try:
                    full_page = self.get_wiki_page(title, repo)
                    content = self._decode_base64(full_page.get('content_base64', ''))
                    # Check if any tag is in the content
                    if not any(tag.lower() in content.lower() for tag in tags):
                        continue
                except Exception:
                    continue
            results.append(page)
        return results
    def _sanitize_page_name(self, title: str) -> str:
        """Convert title to valid wiki page name."""
        # Replace spaces with hyphens, remove special chars
        name = re.sub(r'[^\w\s-]', '', title)
        name = re.sub(r'[\s]+', '-', name)
        return name.lower()
    # ========================================
    # MILESTONE OPERATIONS
    # ========================================
    def list_milestones(
        self,
        state: str = 'open',
        repo: Optional[str] = None
    ) -> List[Dict]:
        """List all milestones in repository."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/milestones"
        params = {'state': state}
        logger.info(f"Listing milestones from {owner}/{target_repo}")
        response = self.session.get(url, params=params)
        response.raise_for_status()
        return response.json()
    def get_milestone(
        self,
        milestone_id: int,
        repo: Optional[str] = None
    ) -> Dict:
        """Get a specific milestone by ID."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/milestones/{milestone_id}"
        logger.info(f"Getting milestone #{milestone_id} from {owner}/{target_repo}")
        response = self.session.get(url)
        response.raise_for_status()
        return response.json()
    def create_milestone(
        self,
        title: str,
        description: Optional[str] = None,
        due_on: Optional[str] = None,
        repo: Optional[str] = None
    ) -> Dict:
        """Create a new milestone."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/milestones"
        data = {'title': title}
        if description:
            data['description'] = description
        if due_on:
            data['due_on'] = due_on
        logger.info(f"Creating milestone '{title}' in {owner}/{target_repo}")
        response = self.session.post(url, json=data)
        response.raise_for_status()
        return response.json()
    def update_milestone(
        self,
        milestone_id: int,
        title: Optional[str] = None,
        description: Optional[str] = None,
        state: Optional[str] = None,
        due_on: Optional[str] = None,
        repo: Optional[str] = None
    ) -> Dict:
        """Update an existing milestone."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/milestones/{milestone_id}"
        data = {}
        if title is not None:
            data['title'] = title
        if description is not None:
            data['description'] = description
        if state is not None:
            data['state'] = state
        if due_on is not None:
            data['due_on'] = due_on
        logger.info(f"Updating milestone #{milestone_id} in {owner}/{target_repo}")
        response = self.session.patch(url, json=data)
        response.raise_for_status()
        return response.json()
    def delete_milestone(
        self,
        milestone_id: int,
        repo: Optional[str] = None
    ) -> bool:
        """Delete a milestone."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/milestones/{milestone_id}"
        logger.info(f"Deleting milestone #{milestone_id} from {owner}/{target_repo}")
        response = self.session.delete(url)
        response.raise_for_status()
        return True
    # ========================================
    # ISSUE DEPENDENCY OPERATIONS
    # ========================================
    def list_issue_dependencies(
        self,
        issue_number: int,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """List all dependencies for an issue (issues that block this one)."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/issues/{issue_number}/dependencies"
        logger.info(f"Listing dependencies for issue #{issue_number} in {owner}/{target_repo}")
        response = self.session.get(url)
        response.raise_for_status()
        return response.json()
    def create_issue_dependency(
        self,
        issue_number: int,
        depends_on: int,
        repo: Optional[str] = None
    ) -> Dict:
        """Create a dependency (issue_number depends on depends_on)."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/issues/{issue_number}/dependencies"
        data = {
            'dependentIssue': {
                'owner': owner,
                'repo': target_repo,
                'index': depends_on
            }
        }
        logger.info(f"Creating dependency: #{issue_number} depends on #{depends_on} in {owner}/{target_repo}")
        response = self.session.post(url, json=data)
        response.raise_for_status()
        return response.json()
    def remove_issue_dependency(
        self,
        issue_number: int,
        depends_on: int,
        repo: Optional[str] = None
    ) -> bool:
        """Remove a dependency between issues."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/issues/{issue_number}/dependencies"
        data = {
            'dependentIssue': {
                'owner': owner,
                'repo': target_repo,
                'index': depends_on
            }
        }
        logger.info(f"Removing dependency: #{issue_number} no longer depends on #{depends_on}")
        response = self.session.delete(url, json=data)
        response.raise_for_status()
        return True
    def list_issue_blocks(
        self,
        issue_number: int,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """List all issues that this issue blocks."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/issues/{issue_number}/blocks"
        logger.info(f"Listing issues blocked by #{issue_number} in {owner}/{target_repo}")
        response = self.session.get(url)
        response.raise_for_status()
        return response.json()
    # ========================================
    # REPOSITORY VALIDATION
    # ========================================
    def get_repo_info(self, repo: Optional[str] = None) -> Dict:
        """Get repository information including owner type."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}"
        logger.info(f"Getting repo info for {owner}/{target_repo}")
        response = self.session.get(url)
        response.raise_for_status()
        return response.json()
    def is_org_repo(self, repo: Optional[str] = None) -> bool:
        """Check if repository belongs to an organization (not a user)."""
        info = self.get_repo_info(repo)
        owner_type = info.get('owner', {}).get('type', '')
        return owner_type.lower() == 'organization'
    def get_branch_protection(
        self,
        branch: str,
        repo: Optional[str] = None
    ) -> Optional[Dict]:
        """Get branch protection rules for a branch."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/branch_protections/{branch}"
        logger.info(f"Getting branch protection for {branch} in {owner}/{target_repo}")
        try:
            response = self.session.get(url)
            response.raise_for_status()
            return response.json()
        except requests.exceptions.HTTPError as e:
            if e.response.status_code == 404:
                return None  # No protection rules
            raise
    def create_label(
        self,
        name: str,
        color: str,
        description: Optional[str] = None,
        repo: Optional[str] = None
    ) -> Dict:
        """Create a new label in the repository."""
        owner, target_repo = self._parse_repo(repo)
        url = f"{self.base_url}/repos/{owner}/{target_repo}/labels"
        data = {
            'name': name,
            'color': color.lstrip('#')  # Remove # if present
        }
        if description:
            data['description'] = description
        logger.info(f"Creating label '{name}' in {owner}/{target_repo}")
        response = self.session.post(url, json=data)
        response.raise_for_status()
        return response.json()
--- a/plugins/projman/mcp-servers/gitea/mcp_server/server.py
+++ b/plugins/projman/mcp-servers/gitea/mcp_server/server.py
@@ -14,6 +14,9 @@ from .config import GiteaConfig
 from .gitea_client import GiteaClient
 from .tools.issues import IssueTools
 from .tools.labels import LabelTools
 from .tools.wiki import WikiTools
 from .tools.milestones import MilestoneTools
 from .tools.dependencies import DependencyTools
 # Suppress noisy MCP validation warnings on stderr
 logging.basicConfig(level=logging.INFO)
@@ -31,6 +34,9 @@ class GiteaMCPServer:
        self.client = None
        self.issue_tools = None
        self.label_tools = None
        self.wiki_tools = None
        self.milestone_tools = None
        self.dependency_tools = None
    async def initialize(self):
        """
@@ -46,6 +52,9 @@ class GiteaMCPServer:
            self.client = GiteaClient()
            self.issue_tools = IssueTools(self.client)
            self.label_tools = LabelTools(self.client)
            self.wiki_tools = WikiTools(self.client)
            self.milestone_tools = MilestoneTools(self.client)
            self.dependency_tools = DependencyTools(self.client)
            logger.info(f"Gitea MCP Server initialized in {self.config['mode']} mode")
        except Exception as e:
@@ -237,6 +246,398 @@ class GiteaMCPServer:
                        },
                        "required": ["org"]
                    }
                ),
                # Wiki Tools (Lessons Learned)
                Tool(
                    name="list_wiki_pages",
                    description="List all wiki pages in repository",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        }
                    }
                ),
                Tool(
                    name="get_wiki_page",
                    description="Get a specific wiki page by name",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "page_name": {
                                "type": "string",
                                "description": "Wiki page name/path"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["page_name"]
                    }
                ),
                Tool(
                    name="create_wiki_page",
                    description="Create a new wiki page",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "title": {
                                "type": "string",
                                "description": "Page title/name"
                            },
                            "content": {
                                "type": "string",
                                "description": "Page content (markdown)"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["title", "content"]
                    }
                ),
                Tool(
                    name="update_wiki_page",
                    description="Update an existing wiki page",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "page_name": {
                                "type": "string",
                                "description": "Wiki page name/path"
                            },
                            "content": {
                                "type": "string",
                                "description": "New page content (markdown)"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["page_name", "content"]
                    }
                ),
                Tool(
                    name="create_lesson",
                    description="Create a lessons learned entry in the wiki",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "title": {
                                "type": "string",
                                "description": "Lesson title (e.g., 'Sprint 16 - Prevent Infinite Loops')"
                            },
                            "content": {
                                "type": "string",
                                "description": "Lesson content (markdown with context, problem, solution, prevention)"
                            },
                            "tags": {
                                "type": "array",
                                "items": {"type": "string"},
                                "description": "Tags for categorization"
                            },
                            "category": {
                                "type": "string",
                                "default": "sprints",
                                "description": "Category (sprints, patterns, architecture, etc.)"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["title", "content", "tags"]
                    }
                ),
                Tool(
                    name="search_lessons",
                    description="Search lessons learned from previous sprints",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "query": {
                                "type": "string",
                                "description": "Search query (optional)"
                            },
                            "tags": {
                                "type": "array",
                                "items": {"type": "string"},
                                "description": "Tags to filter by (optional)"
                            },
                            "limit": {
                                "type": "integer",
                                "default": 20,
                                "description": "Maximum results"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        }
                    }
                ),
                # Milestone Tools
                Tool(
                    name="list_milestones",
                    description="List all milestones in repository",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "state": {
                                "type": "string",
                                "enum": ["open", "closed", "all"],
                                "default": "open",
                                "description": "Milestone state filter"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        }
                    }
                ),
                Tool(
                    name="get_milestone",
                    description="Get a specific milestone by ID",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "milestone_id": {
                                "type": "integer",
                                "description": "Milestone ID"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["milestone_id"]
                    }
                ),
                Tool(
                    name="create_milestone",
                    description="Create a new milestone",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "title": {
                                "type": "string",
                                "description": "Milestone title"
                            },
                            "description": {
                                "type": "string",
                                "description": "Milestone description"
                            },
                            "due_on": {
                                "type": "string",
                                "description": "Due date (ISO 8601 format)"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["title"]
                    }
                ),
                Tool(
                    name="update_milestone",
                    description="Update an existing milestone",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "milestone_id": {
                                "type": "integer",
                                "description": "Milestone ID"
                            },
                            "title": {
                                "type": "string",
                                "description": "New title"
                            },
                            "description": {
                                "type": "string",
                                "description": "New description"
                            },
                            "state": {
                                "type": "string",
                                "enum": ["open", "closed"],
                                "description": "New state"
                            },
                            "due_on": {
                                "type": "string",
                                "description": "New due date"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["milestone_id"]
                    }
                ),
                Tool(
                    name="delete_milestone",
                    description="Delete a milestone",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "milestone_id": {
                                "type": "integer",
                                "description": "Milestone ID"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["milestone_id"]
                    }
                ),
                # Dependency Tools
                Tool(
                    name="list_issue_dependencies",
                    description="List all dependencies for an issue (issues that block this one)",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "issue_number": {
                                "type": "integer",
                                "description": "Issue number"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["issue_number"]
                    }
                ),
                Tool(
                    name="create_issue_dependency",
                    description="Create a dependency (issue depends on another issue)",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "issue_number": {
                                "type": "integer",
                                "description": "Issue that will depend on another"
                            },
                            "depends_on": {
                                "type": "integer",
                                "description": "Issue that blocks issue_number"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["issue_number", "depends_on"]
                    }
                ),
                Tool(
                    name="remove_issue_dependency",
                    description="Remove a dependency between issues",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "issue_number": {
                                "type": "integer",
                                "description": "Issue that depends on another"
                            },
                            "depends_on": {
                                "type": "integer",
                                "description": "Issue being depended on"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["issue_number", "depends_on"]
                    }
                ),
                Tool(
                    name="get_execution_order",
                    description="Get parallelizable execution order for issues based on dependencies",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "issue_numbers": {
                                "type": "array",
                                "items": {"type": "integer"},
                                "description": "List of issue numbers to analyze"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["issue_numbers"]
                    }
                ),
                # Validation Tools
                Tool(
                    name="validate_repo_org",
                    description="Check if repository belongs to an organization",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        }
                    }
                ),
                Tool(
                    name="get_branch_protection",
                    description="Get branch protection rules",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "branch": {
                                "type": "string",
                                "description": "Branch name"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["branch"]
                    }
                ),
                Tool(
                    name="create_label",
                    description="Create a new label in the repository",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "name": {
                                "type": "string",
                                "description": "Label name"
                            },
                            "color": {
                                "type": "string",
                                "description": "Label color (hex code)"
                            },
                            "description": {
                                "type": "string",
                                "description": "Label description"
                            },
                            "repo": {
                                "type": "string",
                                "description": "Repository name (owner/repo format)"
                            }
                        },
                        "required": ["name", "color"]
                    }
                )
            ]
@@ -270,6 +671,61 @@ class GiteaMCPServer:
                    result = await self.label_tools.suggest_labels(**arguments)
                elif name == "aggregate_issues":
                    result = await self.issue_tools.aggregate_issues(**arguments)
                # Wiki tools
                elif name == "list_wiki_pages":
                    result = await self.wiki_tools.list_wiki_pages(**arguments)
                elif name == "get_wiki_page":
                    result = await self.wiki_tools.get_wiki_page(**arguments)
                elif name == "create_wiki_page":
                    result = await self.wiki_tools.create_wiki_page(**arguments)
                elif name == "update_wiki_page":
                    result = await self.wiki_tools.update_wiki_page(**arguments)
                elif name == "create_lesson":
                    result = await self.wiki_tools.create_lesson(**arguments)
                elif name == "search_lessons":
                    tags = arguments.get('tags')
                    result = await self.wiki_tools.search_lessons(
                        query=arguments.get('query'),
                        tags=tags,
                        limit=arguments.get('limit', 20),
                        repo=arguments.get('repo')
                    )
                # Milestone tools
                elif name == "list_milestones":
                    result = await self.milestone_tools.list_milestones(**arguments)
                elif name == "get_milestone":
                    result = await self.milestone_tools.get_milestone(**arguments)
                elif name == "create_milestone":
                    result = await self.milestone_tools.create_milestone(**arguments)
                elif name == "update_milestone":
                    result = await self.milestone_tools.update_milestone(**arguments)
                elif name == "delete_milestone":
                    result = await self.milestone_tools.delete_milestone(**arguments)
                # Dependency tools
                elif name == "list_issue_dependencies":
                    result = await self.dependency_tools.list_issue_dependencies(**arguments)
                elif name == "create_issue_dependency":
                    result = await self.dependency_tools.create_issue_dependency(**arguments)
                elif name == "remove_issue_dependency":
                    result = await self.dependency_tools.remove_issue_dependency(**arguments)
                elif name == "get_execution_order":
                    result = await self.dependency_tools.get_execution_order(**arguments)
                # Validation tools
                elif name == "validate_repo_org":
                    is_org = self.client.is_org_repo(arguments.get('repo'))
                    result = {'is_organization': is_org}
                elif name == "get_branch_protection":
                    result = self.client.get_branch_protection(
                        arguments['branch'],
                        arguments.get('repo')
                    )
                elif name == "create_label":
                    result = self.client.create_label(
                        arguments['name'],
                        arguments['color'],
                        arguments.get('description'),
                        arguments.get('repo')
                    )
                else:
                    raise ValueError(f"Unknown tool: {name}")
--- a/plugins/projman/mcp-servers/gitea/mcp_server/tools/dependencies.py
+++ b/plugins/projman/mcp-servers/gitea/mcp_server/tools/dependencies.py
@@ -0,0 +1,216 @@
 """
 Issue dependency management tools for MCP server.
 Provides async wrappers for issue dependency operations:
 - List/create/remove dependencies
 - Build dependency graphs for parallel execution
 """
 import asyncio
 import logging
 from typing import List, Dict, Optional, Set, Tuple
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 class DependencyTools:
    """Async wrappers for Gitea issue dependency operations"""
    def __init__(self, gitea_client):
        """
        Initialize dependency tools.
        Args:
            gitea_client: GiteaClient instance
        """
        self.gitea = gitea_client
    async def list_issue_dependencies(
        self,
        issue_number: int,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """
        List all dependencies for an issue (issues that block this one).
        Args:
            issue_number: Issue number
            repo: Repository in owner/repo format
        Returns:
            List of issues that this issue depends on
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.list_issue_dependencies(issue_number, repo)
        )
    async def create_issue_dependency(
        self,
        issue_number: int,
        depends_on: int,
        repo: Optional[str] = None
    ) -> Dict:
        """
        Create a dependency between issues.
        Args:
            issue_number: The issue that will depend on another
            depends_on: The issue that blocks issue_number
            repo: Repository in owner/repo format
        Returns:
            Created dependency information
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.create_issue_dependency(issue_number, depends_on, repo)
        )
    async def remove_issue_dependency(
        self,
        issue_number: int,
        depends_on: int,
        repo: Optional[str] = None
    ) -> bool:
        """
        Remove a dependency between issues.
        Args:
            issue_number: The issue that currently depends on another
            depends_on: The issue being depended on
            repo: Repository in owner/repo format
        Returns:
            True if removed successfully
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.remove_issue_dependency(issue_number, depends_on, repo)
        )
    async def list_issue_blocks(
        self,
        issue_number: int,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """
        List all issues that this issue blocks.
        Args:
            issue_number: Issue number
            repo: Repository in owner/repo format
        Returns:
            List of issues blocked by this issue
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.list_issue_blocks(issue_number, repo)
        )
    async def build_dependency_graph(
        self,
        issue_numbers: List[int],
        repo: Optional[str] = None
    ) -> Dict[int, List[int]]:
        """
        Build a dependency graph for a list of issues.
        Args:
            issue_numbers: List of issue numbers to analyze
            repo: Repository in owner/repo format
        Returns:
            Dictionary mapping issue_number -> list of issues it depends on
        """
        graph = {}
        for issue_num in issue_numbers:
            try:
                deps = await self.list_issue_dependencies(issue_num, repo)
                graph[issue_num] = [
                    d.get('number') or d.get('index')
                    for d in deps
                    if (d.get('number') or d.get('index')) in issue_numbers
                ]
            except Exception as e:
                logger.warning(f"Could not fetch dependencies for #{issue_num}: {e}")
                graph[issue_num] = []
        return graph
    async def get_ready_tasks(
        self,
        issue_numbers: List[int],
        completed: Set[int],
        repo: Optional[str] = None
    ) -> List[int]:
        """
        Get tasks that are ready to execute (no unresolved dependencies).
        Args:
            issue_numbers: List of all issue numbers in sprint
            completed: Set of already completed issue numbers
            repo: Repository in owner/repo format
        Returns:
            List of issue numbers that can be executed now
        """
        graph = await self.build_dependency_graph(issue_numbers, repo)
        ready = []
        for issue_num in issue_numbers:
            if issue_num in completed:
                continue
            deps = graph.get(issue_num, [])
            # Task is ready if all its dependencies are completed
            if all(dep in completed for dep in deps):
                ready.append(issue_num)
        return ready
    async def get_execution_order(
        self,
        issue_numbers: List[int],
        repo: Optional[str] = None
    ) -> List[List[int]]:
        """
        Get a parallelizable execution order for issues.
        Returns batches of issues that can be executed in parallel.
        Each batch contains issues with no unresolved dependencies.
        Args:
            issue_numbers: List of all issue numbers
            repo: Repository in owner/repo format
        Returns:
            List of batches, where each batch can be executed in parallel
        """
        graph = await self.build_dependency_graph(issue_numbers, repo)
        completed: Set[int] = set()
        remaining = set(issue_numbers)
        batches = []
        while remaining:
            # Find all tasks with no unresolved dependencies
            batch = []
            for issue_num in remaining:
                deps = graph.get(issue_num, [])
                if all(dep in completed for dep in deps):
                    batch.append(issue_num)
            if not batch:
                # Circular dependency detected
                logger.error(f"Circular dependency detected! Remaining: {remaining}")
                batch = list(remaining)  # Force include remaining to avoid infinite loop
            batches.append(batch)
            completed.update(batch)
            remaining -= set(batch)
        return batches
--- a/plugins/projman/mcp-servers/gitea/mcp_server/tools/milestones.py
+++ b/plugins/projman/mcp-servers/gitea/mcp_server/tools/milestones.py
@@ -0,0 +1,145 @@
 """
 Milestone management tools for MCP server.
 Provides async wrappers for milestone operations:
 - CRUD operations for milestones
 - Milestone-sprint relationship tracking
 """
 import asyncio
 import logging
 from typing import List, Dict, Optional
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 class MilestoneTools:
    """Async wrappers for Gitea milestone operations"""
    def __init__(self, gitea_client):
        """
        Initialize milestone tools.
        Args:
            gitea_client: GiteaClient instance
        """
        self.gitea = gitea_client
    async def list_milestones(
        self,
        state: str = 'open',
        repo: Optional[str] = None
    ) -> List[Dict]:
        """
        List all milestones in repository.
        Args:
            state: Milestone state (open, closed, all)
            repo: Repository in owner/repo format
        Returns:
            List of milestone dictionaries
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.list_milestones(state, repo)
        )
    async def get_milestone(
        self,
        milestone_id: int,
        repo: Optional[str] = None
    ) -> Dict:
        """
        Get a specific milestone by ID.
        Args:
            milestone_id: Milestone ID
            repo: Repository in owner/repo format
        Returns:
            Milestone dictionary
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.get_milestone(milestone_id, repo)
        )
    async def create_milestone(
        self,
        title: str,
        description: Optional[str] = None,
        due_on: Optional[str] = None,
        repo: Optional[str] = None
    ) -> Dict:
        """
        Create a new milestone.
        Args:
            title: Milestone title (e.g., "v2.0 Release", "Sprint 17")
            description: Milestone description
            due_on: Due date in ISO 8601 format (e.g., "2025-02-01T00:00:00Z")
            repo: Repository in owner/repo format
        Returns:
            Created milestone dictionary
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.create_milestone(title, description, due_on, repo)
        )
    async def update_milestone(
        self,
        milestone_id: int,
        title: Optional[str] = None,
        description: Optional[str] = None,
        state: Optional[str] = None,
        due_on: Optional[str] = None,
        repo: Optional[str] = None
    ) -> Dict:
        """
        Update an existing milestone.
        Args:
            milestone_id: Milestone ID
            title: New title (optional)
            description: New description (optional)
            state: New state - 'open' or 'closed' (optional)
            due_on: New due date (optional)
            repo: Repository in owner/repo format
        Returns:
            Updated milestone dictionary
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.update_milestone(
                milestone_id, title, description, state, due_on, repo
            )
        )
    async def delete_milestone(
        self,
        milestone_id: int,
        repo: Optional[str] = None
    ) -> bool:
        """
        Delete a milestone.
        Args:
            milestone_id: Milestone ID
            repo: Repository in owner/repo format
        Returns:
            True if deleted successfully
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.delete_milestone(milestone_id, repo)
        )
--- a/plugins/projman/mcp-servers/gitea/mcp_server/tools/wiki.py
+++ b/plugins/projman/mcp-servers/gitea/mcp_server/tools/wiki.py
@@ -0,0 +1,149 @@
 """
 Wiki management tools for MCP server.
 Provides async wrappers for wiki operations to support lessons learned:
 - Page CRUD operations
 - Lessons learned creation and search
 """
 import asyncio
 import logging
 from typing import List, Dict, Optional
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 class WikiTools:
    """Async wrappers for Gitea wiki operations"""
    def __init__(self, gitea_client):
        """
        Initialize wiki tools.
        Args:
            gitea_client: GiteaClient instance
        """
        self.gitea = gitea_client
    async def list_wiki_pages(self, repo: Optional[str] = None) -> List[Dict]:
        """List all wiki pages in repository."""
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.list_wiki_pages(repo)
        )
    async def get_wiki_page(
        self,
        page_name: str,
        repo: Optional[str] = None
    ) -> Dict:
        """Get a specific wiki page by name."""
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.get_wiki_page(page_name, repo)
        )
    async def create_wiki_page(
        self,
        title: str,
        content: str,
        repo: Optional[str] = None
    ) -> Dict:
        """Create a new wiki page."""
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.create_wiki_page(title, content, repo)
        )
    async def update_wiki_page(
        self,
        page_name: str,
        content: str,
        repo: Optional[str] = None
    ) -> Dict:
        """Update an existing wiki page."""
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.update_wiki_page(page_name, content, repo)
        )
    async def delete_wiki_page(
        self,
        page_name: str,
        repo: Optional[str] = None
    ) -> bool:
        """Delete a wiki page."""
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.delete_wiki_page(page_name, repo)
        )
    async def search_wiki_pages(
        self,
        query: str,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """Search wiki pages by title."""
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.search_wiki_pages(query, repo)
        )
    async def create_lesson(
        self,
        title: str,
        content: str,
        tags: List[str],
        category: str = "sprints",
        repo: Optional[str] = None
    ) -> Dict:
        """
        Create a lessons learned entry in the wiki.
        Args:
            title: Lesson title (e.g., "Sprint 16 - Prevent Infinite Loops")
            content: Lesson content in markdown
            tags: List of tags for categorization
            category: Category (sprints, patterns, architecture, etc.)
            repo: Repository in owner/repo format
        Returns:
            Created wiki page
        """
        loop = asyncio.get_event_loop()
        return await loop.run_in_executor(
            None,
            lambda: self.gitea.create_lesson(title, content, tags, category, repo)
        )
    async def search_lessons(
        self,
        query: Optional[str] = None,
        tags: Optional[List[str]] = None,
        limit: int = 20,
        repo: Optional[str] = None
    ) -> List[Dict]:
        """
        Search lessons learned from previous sprints.
        Args:
            query: Search query (optional)
            tags: Tags to filter by (optional)
            limit: Maximum results (default 20)
            repo: Repository in owner/repo format
        Returns:
            List of matching lessons
        """
        loop = asyncio.get_event_loop()
        results = await loop.run_in_executor(
            None,
            lambda: self.gitea.search_lessons(query, tags, repo)
        )
        return results[:limit]
--- a/plugins/projman/mcp-servers/wikijs/README.md
+++ b/plugins/projman/mcp-servers/wikijs/README.md
@@ -1,413 +0,0 @@
 # Wiki.js MCP Server
 Model Context Protocol (MCP) server for Wiki.js integration with Claude Code.
 ## Overview
 The Wiki.js MCP Server provides Claude Code with direct access to Wiki.js for documentation management, lessons learned capture, and knowledge base operations. It supports both single-project (project mode) and company-wide (PMO mode) operations.
 **Status**: ✅ Phase 1.1b Complete - Fully functional and tested
 ## Features
 ### Core Functionality
 - **Page Management**: CRUD operations for Wiki.js pages with markdown content
 - **Lessons Learned**: Systematic capture and searchable repository of sprint insights
 - **Mode Detection**: Automatic project vs company-wide mode detection
 - **Hybrid Configuration**: System-level credentials + project-level paths
 - **PMO Support**: Company-wide documentation and cross-project lesson search
 ### Tools Provided
 | Tool | Description | Mode |
 |------|-------------|------|
 | `search_pages` | Search pages by keywords and tags | Both |
 | `get_page` | Get specific page content | Both |
 | `create_page` | Create new page with markdown content | Both |
 | `update_page` | Update existing page | Both |
 | `list_pages` | List pages under a path | Both |
 | `create_lesson` | Create lessons learned entry | Both |
 | `search_lessons` | Search lessons from previous sprints | Both |
 | `tag_lesson` | Add/update tags on lessons | Both |
 ## Architecture
 ### Directory Structure
 ```
 mcp-servers/wikijs/
 ├── .venv/                      # Python virtual environment
 ├── requirements.txt            # Python dependencies
 ├── mcp_server/
 │   ├── __init__.py
 │   ├── server.py              # MCP server entry point
 │   ├── config.py              # Configuration loader
 │   ├── wikijs_client.py       # Wiki.js GraphQL client
 │   └── tools/
 │       ├── __init__.py
 │       ├── pages.py           # Page management tools
 │       └── lessons_learned.py # Lessons learned tools
 ├── tests/
 │   ├── __init__.py
 │   ├── test_config.py
 │   └── test_wikijs_client.py
 ├── README.md                   # This file
 └── TESTING.md                  # Testing instructions
 ```
 ### Mode Detection
 The server operates in two modes based on environment variables:
 **Project Mode** (Single Project):
 - When `WIKIJS_PROJECT` is set
 - Operates on single project path
 - Used by `projman` plugin
 - Pages scoped to `/base_path/project/`
 **Company Mode** (Multi-Project / PMO):
 - When `WIKIJS_PROJECT` is NOT set
 - Operates on all projects in organization
 - Used by `projman-pmo` plugin
 - Pages scoped to `/base_path/`
 ### GraphQL Integration
 The server uses Wiki.js GraphQL API for all operations:
 - **Pages API**: Create, read, update, list, search pages
 - **Tags**: Categorize and filter content
 - **Search**: Full-text search with tag filtering
 - **Lessons Learned**: Specialized workflow for sprint insights
 ## Installation
 ### Prerequisites
 - Python 3.10 or higher
 - Access to Wiki.js instance with API token
 - GraphQL API enabled on Wiki.js
 ### Step 1: Install Dependencies
 ```bash
 cd mcp-servers/wikijs
 python3 -m venv .venv
 source .venv/bin/activate  # Linux/Mac
 # or .venv\Scripts\activate  # Windows
 pip install -r requirements.txt
 ```
 ### Step 2: System Configuration
 Create system-level configuration with credentials:
 ```bash
 mkdir -p ~/.config/claude
 cat > ~/.config/claude/wikijs.env << 'EOF'
 # Wiki.js API Configuration
 WIKIJS_API_URL=http://wikijs.hotport/graphql
 WIKIJS_API_TOKEN=your_api_token_here
 WIKIJS_BASE_PATH=/your-org
 EOF
 chmod 600 ~/.config/claude/wikijs.env
 ```
 **Obtaining Wiki.js API Token:**
 1. Log in to Wiki.js as administrator
 2. Navigate to Administration → API Access
 3. Click "New API Key"
 4. Set permissions: Pages (read/write), Search (read)
 5. Copy the generated JWT token
 ### Step 3: Project Configuration (Optional)
 For project-scoped operations, create `.env` in project root:
 ```bash
 # In your project directory
 cat > .env << 'EOF'
 # Wiki.js project path
 WIKIJS_PROJECT=projects/your-project-name
 EOF
 # Add to .gitignore
 echo ".env" >> .gitignore
 ```
 **Note:** Omit `.env` for company-wide (PMO) mode.
 ## Usage
 ### Running the MCP Server
 ```bash
 cd mcp-servers/wikijs
 source .venv/bin/activate
 python -m mcp_server.server
 ```
 The server runs as a stdio-based MCP server and communicates via JSON-RPC 2.0.
 ### Integration with Claude Code
 The MCP server is referenced in plugin `.mcp.json`:
 ```json
 {
  "mcpServers": {
    "wikijs": {
      "command": "python",
      "args": ["-m", "mcp_server.server"],
      "cwd": "${CLAUDE_PLUGIN_ROOT}/../mcp-servers/wikijs",
      "env": {}
    }
  }
 }
 ```
 ### Example Tool Calls
 **Search Pages:**
 ```json
 {
  "name": "search_pages",
  "arguments": {
    "query": "API documentation",
    "tags": "backend,api",
    "limit": 10
  }
 }
 ```
 **Create Lesson Learned:**
 ```json
 {
  "name": "create_lesson",
  "arguments": {
    "title": "Sprint 16 - Prevent Claude Code Infinite Loops",
    "content": "## Problem\\n\\nClaude Code entered infinite loop...\\n\\n## Solution\\n\\n...",
    "tags": "claude-code,testing,validation",
    "category": "sprints"
  }
 }
 ```
 **Search Lessons:**
 ```json
 {
  "name": "search_lessons",
  "arguments": {
    "query": "validation",
    "tags": "testing,claude-code",
    "limit": 20
  }
 }
 ```
 ## Configuration Reference
 ### Required Variables
 | Variable | Description | Example |
 |----------|-------------|---------|
 | `WIKIJS_API_URL` | Wiki.js GraphQL endpoint | `http://wiki.example.com/graphql` |
 | `WIKIJS_API_TOKEN` | API authentication token (JWT) | `eyJhbGciOiJSUzI1...` |
 | `WIKIJS_BASE_PATH` | Base path in Wiki.js | `/your-org` |
 ### Optional Variables
 | Variable | Description | Mode |
 |----------|-------------|------|
 | `WIKIJS_PROJECT` | Project-specific path | Project mode only |
 ### Configuration Priority
 1. Project-level `.env` (overrides system)
 2. System-level `~/.config/claude/wikijs.env`
 ## Wiki.js Structure
 ### Recommended Organization
 ```
 /your-org/                  # Base path
 ├── projects/                      # Project-specific
 │   ├── your-project/
 │   │   ├── lessons-learned/
 │   │   │   ├── sprints/
 │   │   │   ├── patterns/
 │   │   │   └── INDEX.md
 │   │   └── documentation/
 │   ├── another-project/
 │   └── shared-library/
 ├── company/                       # Company-wide
 │   ├── processes/
 │   ├── standards/
 │   └── tools/
 └── shared/                        # Cross-project
    ├── architecture-patterns/
    ├── best-practices/
    └── tech-stack/
 ```
 ### Lessons Learned Categories
 - **sprints/**: Sprint-specific lessons and retrospectives
 - **patterns/**: Recurring patterns and solutions
 - **architecture/**: Architectural decisions and outcomes
 - **tools/**: Tool-specific tips and gotchas
 ## Testing
 See [TESTING.md](./TESTING.md) for comprehensive testing instructions.
 **Quick Test:**
 ```bash
 source .venv/bin/activate
 pytest -v
 ```
 **Test Coverage:**
 - 18 tests covering all major functionality
 - Mock-based unit tests (fast)
 - Integration tests with real Wiki.js instance
 - Configuration validation
 - Mode detection
 - Error handling
 ## Lessons Learned System
 ### Why This Matters
 After 15 sprints without systematic lesson capture, repeated mistakes occurred:
 - Claude Code infinite loops on similar issues: 2-3 times
 - Same architectural mistakes: Multiple occurrences
 - Forgotten optimizations: Re-discovered each time
 **Solution:** Mandatory lessons learned capture at sprint close, searchable at sprint start.
 ### Workflow
 **Sprint Close (Orchestrator):**
 1. Capture what went wrong
 2. Document what went right
 3. Note preventable repetitions
 4. Tag for discoverability
 **Sprint Start (Planner):**
 1. Search relevant lessons by tags/keywords
 2. Review applicable patterns
 3. Apply preventive measures
 4. Avoid known pitfalls
 ### Lesson Structure
 ```markdown
 # Sprint X - [Lesson Title]
 ## Context
 [What were you trying to do?]
 ## Problem
 [What went wrong or what insight emerged?]
 ## Solution
 [How did you solve it?]
 ## Prevention
 [How can this be avoided or optimized in the future?]
 ## Tags
 [Comma-separated tags for search]
 ```
 ## Troubleshooting
 ### Connection Errors
 **Error:** `Failed to connect to Wiki.js GraphQL endpoint`
 **Solutions:**
 - Verify `WIKIJS_API_URL` is correct and includes `/graphql`
 - Check Wiki.js is running and accessible
 - Ensure GraphQL API is enabled in Wiki.js admin settings
 ### Authentication Errors
 **Error:** `Unauthorized` or `Invalid token`
 **Solutions:**
 - Verify API token is correct and not expired
 - Check token has required permissions (Pages: read/write, Search: read)
 - Regenerate token in Wiki.js admin if needed
 ### Permission Errors
 **Error:** `Page creation failed: Permission denied`
 **Solutions:**
 - Verify API key has write permissions
 - Check user/group permissions in Wiki.js
 - Ensure base path exists and is accessible
 ### Mode Detection Issues
 **Error:** Operating in wrong mode
 **Solutions:**
 - Check `WIKIJS_PROJECT` environment variable
 - Clear project `.env` for company mode
 - Verify configuration loading order (project overrides system)
 ## Security Considerations
 1. **Never commit tokens**: Keep `~/.config/claude/wikijs.env` and `.env` out of git
 2. **Token scope**: Use minimum required permissions (Pages + Search)
 3. **Token rotation**: Regenerate tokens periodically
 4. **Access control**: Use Wiki.js groups/permissions for sensitive docs
 5. **Audit logs**: Review Wiki.js audit logs for unexpected operations
 ## Performance
 - **GraphQL queries**: Optimized for minimal data transfer
 - **Search**: Indexed by Wiki.js for fast results
 - **Pagination**: Configurable result limits (default: 20)
 - **Caching**: Wiki.js handles internal caching
 ## Development
 ### Running Tests
 ```bash
 # All tests
 pytest -v
 # Specific test file
 pytest tests/test_config.py -v
 # Integration tests only
 pytest tests/test_wikijs_client.py -v -k integration
 ```
 ### Code Structure
 - `config.py`: Configuration loading and validation
 - `wikijs_client.py`: GraphQL client implementation
 - `server.py`: MCP server setup and tool routing
 - `tools/pages.py`: Page management MCP tools
 - `tools/lessons_learned.py`: Lessons learned MCP tools
 ## License
 MIT License - See repository root for details
 ## Support
 For issues and questions:
 - **Repository**: `ssh://git@hotserv.tailc9b278.ts.net:2222/bandit/support-claude-mktplace.git`
 - **Issues**: Contact repository maintainer
 - **Documentation**: `/docs/references/MCP-WIKIJS.md`
--- a/plugins/projman/mcp-servers/wikijs/TESTING.md
+++ b/plugins/projman/mcp-servers/wikijs/TESTING.md
@@ -1,503 +0,0 @@
 # Testing Guide - Wiki.js MCP Server
 This document provides comprehensive testing instructions for the Wiki.js MCP Server.
 ## Test Suite Overview
 The test suite includes:
 - **18 unit tests** with mocks (fast, no external dependencies)
 - **Integration tests** with real Wiki.js instance (requires live Wiki.js)
 - **Configuration validation** tests
 - **Mode detection** tests
 - **GraphQL client** tests
 - **Error handling** tests
 ## Prerequisites
 ### For Unit Tests (Mocked)
 - Python 3.10+
 - Virtual environment with dependencies installed
 - No external services required
 ### For Integration Tests
 - Everything from unit tests, plus:
 - Running Wiki.js instance
 - Valid API token with permissions
 - System configuration file (`~/.config/claude/wikijs.env`)
 ## Quick Start
 ### Run All Unit Tests
 ```bash
 cd mcp-servers/wikijs
 source .venv/bin/activate
 pytest -v
 ```
 **Expected Output:**
 ```
 ==================== test session starts ====================
 tests/test_config.py::test_load_system_config PASSED   [  5%]
 tests/test_config.py::test_project_config_override PASSED [ 11%]
 ...
 ==================== 18 passed in 0.40s ====================
 ```
 ### Run Integration Tests
 ```bash
 # Set up system configuration first
 mkdir -p ~/.config/claude
 cat > ~/.config/claude/wikijs.env << 'EOF'
 WIKIJS_API_URL=http://wikijs.hotport/graphql
 WIKIJS_API_TOKEN=your_real_token_here
 WIKIJS_BASE_PATH=/your-org
 EOF
 # Run integration tests
 pytest -v -m integration
 ```
 ## Test Categories
 ### 1. Configuration Tests (`test_config.py`)
 Tests the hybrid configuration system and mode detection.
 **Tests:**
 - `test_load_system_config`: System-level config loading
 - `test_project_config_override`: Project overrides system
 - `test_missing_system_config`: Error when config missing
 - `test_missing_required_config`: Validation of required vars
 - `test_mode_detection_project`: Project mode detection
 - `test_mode_detection_company`: Company mode detection
 **Run:**
 ```bash
 pytest tests/test_config.py -v
 ```
 ### 2. Wiki.js Client Tests (`test_wikijs_client.py`)
 Tests the GraphQL client and all Wiki.js operations.
 **Tests:**
 - `test_client_initialization`: Client setup
 - `test_company_mode_initialization`: Company mode setup
 - `test_get_full_path_project_mode`: Path construction (project)
 - `test_get_full_path_company_mode`: Path construction (company)
 - `test_search_pages`: Page search
 - `test_get_page`: Single page retrieval
 - `test_create_page`: Page creation
 - `test_update_page`: Page updates
 - `test_list_pages`: List pages with filtering
 - `test_create_lesson`: Lessons learned creation
 - `test_search_lessons`: Lesson search
 - `test_graphql_error_handling`: Error handling
 **Run:**
 ```bash
 pytest tests/test_wikijs_client.py -v
 ```
 ## Integration Testing
 ### Setup Integration Environment
 **Step 1: Configure Wiki.js**
 Create a test namespace in Wiki.js:
 ```
 /test-integration/
 ├── projects/
 │   └── test-project/
 │       ├── documentation/
 │       └── lessons-learned/
 └── shared/
 ```
 **Step 2: Configure System**
 ```bash
 cat > ~/.config/claude/wikijs.env << 'EOF'
 WIKIJS_API_URL=http://wikijs.hotport/graphql
 WIKIJS_API_TOKEN=your_token_here
 WIKIJS_BASE_PATH=/test-integration
 EOF
 ```
 **Step 3: Configure Project**
 ```bash
 # In test directory
 cat > .env << 'EOF'
 WIKIJS_PROJECT=projects/test-project
 EOF
 ```
 ### Run Integration Tests
 ```bash
 # Mark tests for integration
 pytest -v -m integration
 # Run specific integration test
 pytest tests/test_wikijs_client.py::test_create_page -v -m integration
 ```
 ### Integration Test Scenarios
 **Scenario 1: Page Lifecycle**
 1. Create page with `create_page`
 2. Retrieve with `get_page`
 3. Update with `update_page`
 4. Search for page with `search_pages`
 5. Cleanup (manual via Wiki.js UI)
 **Scenario 2: Lessons Learned Workflow**
 1. Create lesson with `create_lesson`
 2. Search lessons with `search_lessons`
 3. Add tags with `tag_lesson`
 4. Verify searchability
 **Scenario 3: Mode Detection**
 1. Test in project mode (with `WIKIJS_PROJECT`)
 2. Test in company mode (without `WIKIJS_PROJECT`)
 3. Verify path scoping
 ## Manual Testing
 ### Test 1: Create and Retrieve Page
 ```bash
 # Start MCP server
 python -m mcp_server.server
 # In another terminal, send MCP request
 echo '{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_page",
    "arguments": {
      "path": "documentation/test-api",
      "title": "Test API Documentation",
      "content": "# Test API\\n\\nThis is a test page.",
      "tags": "api,testing",
      "publish": true
    }
  }
 }' | python -m mcp_server.server
 ```
 **Expected Result:**
 ```json
 {
  "success": true,
  "page": {
    "id": 123,
    "path": "/your-org/projects/test-project/documentation/test-api",
    "title": "Test API Documentation"
  }
 }
 ```
 ### Test 2: Search Lessons
 ```bash
 echo '{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "search_lessons",
    "arguments": {
      "query": "validation",
      "tags": "testing,claude-code",
      "limit": 10
    }
  }
 }' | python -m mcp_server.server
 ```
 **Expected Result:**
 ```json
 {
  "success": true,
  "count": 2,
  "lessons": [...]
 }
 ```
 ### Test 3: Mode Detection
 **Project Mode:**
 ```bash
 # Create .env with WIKIJS_PROJECT
 echo "WIKIJS_PROJECT=projects/test-project" > .env
 # Start server and check logs
 python -m mcp_server.server 2>&1 | grep "mode"
 ```
 **Expected Log:**
 ```
 INFO:Running in project mode: projects/test-project
 ```
 **Company Mode:**
 ```bash
 # Remove .env
 rm .env
 # Start server and check logs
 python -m mcp_server.server 2>&1 | grep "mode"
 ```
 **Expected Log:**
 ```
 INFO:Running in company-wide mode (PMO)
 ```
 ## Test Data Management
 ### Cleanup Test Data
 After integration tests, clean up test pages in Wiki.js:
 ```bash
 # Via Wiki.js UI
 1. Navigate to /test-integration/
 2. Select test pages
 3. Delete
 # Or via GraphQL (advanced)
 curl -X POST http://wikijs.hotport/graphql \
  -H "Authorization: Bearer $WIKIJS_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "mutation { pages { delete(id: 123) { responseResult { succeeded } } } }"
  }'
 ```
 ### Test Data Fixtures
 For repeatable testing, create fixtures:
 ```python
 # tests/conftest.py
 import pytest
@pytest.fixture
 async def test_page():
    """Create a test page and clean up after"""
    client = WikiJSClient(...)
    page = await client.create_page(
        path="test/fixture-page",
        title="Test Fixture",
        content="# Test"
    )
    yield page
    # Cleanup after test
    await client.delete_page(page['id'])
 ```
 ## Continuous Integration
 ### GitHub Actions / Gitea Actions
 ```yaml
 name: Test Wiki.js MCP Server
 on: [push, pull_request]
 jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.10'
      - name: Install dependencies
        working-directory: mcp-servers/wikijs
        run: |
          python -m venv .venv
          source .venv/bin/activate
          pip install -r requirements.txt
      - name: Run unit tests
        working-directory: mcp-servers/wikijs
        run: |
          source .venv/bin/activate
          pytest -v
      # Integration tests (optional, requires Wiki.js instance)
      - name: Run integration tests
        if: env.WIKIJS_API_TOKEN != ''
        working-directory: mcp-servers/wikijs
        env:
          WIKIJS_API_URL: ${{ secrets.WIKIJS_API_URL }}
          WIKIJS_API_TOKEN: ${{ secrets.WIKIJS_API_TOKEN }}
          WIKIJS_BASE_PATH: /test-integration
        run: |
          source .venv/bin/activate
          pytest -v -m integration
 ```
 ## Debugging Tests
 ### Enable Verbose Logging
 ```bash
 # Set log level to DEBUG
 export PYTHONLOG=DEBUG
 pytest -v -s
 ```
 ### Run Single Test with Debugging
 ```bash
 # Run specific test with print statements visible
 pytest tests/test_config.py::test_load_system_config -v -s
 # Use pytest debugger
 pytest tests/test_config.py::test_load_system_config --pdb
 ```
 ### Inspect GraphQL Queries
 Add logging to see actual GraphQL queries:
 ```python
 # In wikijs_client.py
 async def _execute_query(self, query: str, variables: Optional[Dict[str, Any]] = None):
    logger.info(f"GraphQL Query: {query}")
    logger.info(f"Variables: {variables}")
    # ... rest of method
 ```
 ## Test Coverage
 ### Generate Coverage Report
 ```bash
 pip install pytest-cov
 # Run with coverage
 pytest --cov=mcp_server --cov-report=html
 # Open report
 open htmlcov/index.html
 ```
 **Target Coverage:** 90%+ for all modules
 ## Performance Testing
 ### Benchmark GraphQL Operations
 ```python
 import time
 async def benchmark_search():
    client = WikiJSClient(...)
    start = time.time()
    results = await client.search_pages("test")
    elapsed = time.time() - start
    print(f"Search took {elapsed:.3f}s")
 ```
 **Expected Performance:**
 - Search: < 500ms
 - Get page: < 200ms
 - Create page: < 1s
 - Update page: < 500ms
 ## Common Test Failures
 ### 1. Configuration Not Found
 **Error:**
 ```
 FileNotFoundError: System config not found: ~/.config/claude/wikijs.env
 ```
 **Solution:**
 ```bash
 mkdir -p ~/.config/claude
 cat > ~/.config/claude/wikijs.env << 'EOF'
 WIKIJS_API_URL=http://wikijs.hotport/graphql
 WIKIJS_API_TOKEN=test_token
 WIKIJS_BASE_PATH=/test
 EOF
 ```
 ### 2. GraphQL Connection Error
 **Error:**
 ```
 httpx.ConnectError: Connection refused
 ```
 **Solution:**
 - Verify Wiki.js is running
 - Check `WIKIJS_API_URL` is correct
 - Ensure `/graphql` endpoint is accessible
 ### 3. Permission Denied
 **Error:**
 ```
 ValueError: Failed to create page: Permission denied
 ```
 **Solution:**
 - Regenerate API token with write permissions
 - Check Wiki.js user/group permissions
 - Verify base path exists and is accessible
 ### 4. Environment Variable Pollution
 **Error:**
 ```
 AssertionError: assert 'project' == 'company'
 ```
 **Solution:**
 ```python
 # In test, clear environment
 monkeypatch.delenv('WIKIJS_PROJECT', raising=False)
 ```
 ## Best Practices
 1. **Isolate Tests**: Each test should be independent
 2. **Mock External Calls**: Use mocks for unit tests
 3. **Clean Up Resources**: Delete test pages after integration tests
 4. **Use Fixtures**: Reuse common setup/teardown
 5. **Test Error Cases**: Not just happy paths
 6. **Document Assumptions**: Comment what tests expect
 7. **Consistent Naming**: Follow `test_<what>_<scenario>` pattern
 ## Next Steps
 After testing passes:
 1. Review code coverage report
 2. Add integration tests for edge cases
 3. Document any new test scenarios
 4. Update CI/CD pipeline
 5. Create test data fixtures for common scenarios
 ## Support
 For testing issues:
 - Check test logs: `pytest -v -s`
 - Review Wiki.js logs
 - Verify configuration files
 - See main README.md troubleshooting section
--- a/plugins/projman/mcp-servers/wikijs/mcp_server/init.py
+++ b/plugins/projman/mcp-servers/wikijs/mcp_server/init.py
@@ -1,3 +0,0 @@
 """Wiki.js MCP Server for Claude Code."""
 __version__ = "0.1.0"
--- a/plugins/projman/mcp-servers/wikijs/mcp_server/config.py
+++ b/plugins/projman/mcp-servers/wikijs/mcp_server/config.py
@@ -1,102 +0,0 @@
 """
 Configuration loader for Wiki.js MCP Server.
 Implements hybrid configuration system:
 - System-level: ~/.config/claude/wikijs.env (credentials)
 - Project-level: .env (project path specification)
 """
 from pathlib import Path
 from dotenv import load_dotenv
 import os
 import logging
 from typing import Dict, Optional
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 class WikiJSConfig:
    """Hybrid configuration loader with mode detection"""
    def __init__(self):
        self.api_url: Optional[str] = None
        self.api_token: Optional[str] = None
        self.base_path: Optional[str] = None
        self.project: Optional[str] = None
        self.mode: str = 'project'
    def load(self) -> Dict[str, Optional[str]]:
        """
        Load configuration from system and project levels.
        Project-level configuration overrides system-level.
        Returns:
            Dict containing api_url, api_token, base_path, project, mode
        Raises:
            FileNotFoundError: If system config is missing
            ValueError: If required configuration is missing
        """
        # Load system config
        system_config = Path.home() / '.config' / 'claude' / 'wikijs.env'
        if system_config.exists():
            load_dotenv(system_config)
            logger.info(f"Loaded system configuration from {system_config}")
        else:
            raise FileNotFoundError(
                f"System config not found: {system_config}\n"
                "Create it with: mkdir -p ~/.config/claude && "
                "cat > ~/.config/claude/wikijs.env"
            )
        # Load project config (overrides system)
        project_config = Path.cwd() / '.env'
        if project_config.exists():
            load_dotenv(project_config, override=True)
            logger.info(f"Loaded project configuration from {project_config}")
        # Extract values
        self.api_url = os.getenv('WIKIJS_API_URL')
        self.api_token = os.getenv('WIKIJS_API_TOKEN')
        self.base_path = os.getenv('WIKIJS_BASE_PATH')
        self.project = os.getenv('WIKIJS_PROJECT')  # Optional for PMO
        # Detect mode
        if self.project:
            self.mode = 'project'
            logger.info(f"Running in project mode: {self.project}")
        else:
            self.mode = 'company'
            logger.info("Running in company-wide mode (PMO)")
        # Validate required variables
        self._validate()
        return {
            'api_url': self.api_url,
            'api_token': self.api_token,
            'base_path': self.base_path,
            'project': self.project,
            'mode': self.mode
        }
    def _validate(self) -> None:
        """
        Validate that required configuration is present.
        Raises:
            ValueError: If required configuration is missing
        """
        required = {
            'WIKIJS_API_URL': self.api_url,
            'WIKIJS_API_TOKEN': self.api_token,
            'WIKIJS_BASE_PATH': self.base_path
        }
        missing = [key for key, value in required.items() if not value]
        if missing:
            raise ValueError(
                f"Missing required configuration: {', '.join(missing)}\n"
                "Check your ~/.config/claude/wikijs.env file"
            )
--- a/plugins/projman/mcp-servers/wikijs/mcp_server/server.py
+++ b/plugins/projman/mcp-servers/wikijs/mcp_server/server.py
@@ -1,385 +0,0 @@
 """
 MCP Server entry point for Wiki.js integration.
 Provides Wiki.js tools to Claude Code via JSON-RPC 2.0 over stdio.
 """
 import asyncio
 import logging
 import json
 from mcp.server import Server
 from mcp.server.stdio import stdio_server
 from mcp.types import Tool, TextContent
 from .config import WikiJSConfig
 from .wikijs_client import WikiJSClient
 # Suppress noisy MCP validation warnings on stderr
 logging.basicConfig(level=logging.INFO)
 logging.getLogger("root").setLevel(logging.ERROR)
 logging.getLogger("mcp").setLevel(logging.ERROR)
 logger = logging.getLogger(__name__)
 class WikiJSMCPServer:
    """MCP Server for Wiki.js integration"""
    def __init__(self):
        self.server = Server("wikijs-mcp")
        self.config = None
        self.client = None
    async def initialize(self):
        """
        Initialize server and load configuration.
        Raises:
            Exception: If initialization fails
        """
        try:
            config_loader = WikiJSConfig()
            self.config = config_loader.load()
            self.client = WikiJSClient(
                api_url=self.config['api_url'],
                api_token=self.config['api_token'],
                base_path=self.config['base_path'],
                project=self.config.get('project')
            )
            logger.info(f"Wiki.js MCP Server initialized in {self.config['mode']} mode")
        except Exception as e:
            logger.error(f"Failed to initialize: {e}")
            raise
    def setup_tools(self):
        """Register all available tools with the MCP server"""
        @self.server.list_tools()
        async def list_tools() -> list[Tool]:
            """Return list of available tools"""
            return [
                Tool(
                    name="search_pages",
                    description="Search Wiki.js pages by keywords and tags",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "query": {
                                "type": "string",
                                "description": "Search query string"
                            },
                            "tags": {
                                "type": "string",
                                "description": "Comma-separated tags to filter by (optional)"
                            },
                            "limit": {
                                "type": "integer",
                                "default": 20,
                                "description": "Maximum results to return"
                            }
                        },
                        "required": ["query"]
                    }
                ),
                Tool(
                    name="get_page",
                    description="Get a specific page by path",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "path": {
                                "type": "string",
                                "description": "Page path (relative or absolute)"
                            }
                        },
                        "required": ["path"]
                    }
                ),
                Tool(
                    name="create_page",
                    description="Create a new Wiki.js page",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "path": {
                                "type": "string",
                                "description": "Page path relative to project/base"
                            },
                            "title": {
                                "type": "string",
                                "description": "Page title"
                            },
                            "content": {
                                "type": "string",
                                "description": "Page content (markdown)"
                            },
                            "description": {
                                "type": "string",
                                "description": "Page description (optional)"
                            },
                            "tags": {
                                "type": "string",
                                "description": "Comma-separated tags (optional)"
                            },
                            "publish": {
                                "type": "boolean",
                                "default": True,
                                "description": "Publish immediately"
                            }
                        },
                        "required": ["path", "title", "content"]
                    }
                ),
                Tool(
                    name="update_page",
                    description="Update an existing Wiki.js page",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "page_id": {
                                "type": "integer",
                                "description": "Page ID"
                            },
                            "content": {
                                "type": "string",
                                "description": "New content (optional)"
                            },
                            "title": {
                                "type": "string",
                                "description": "New title (optional)"
                            },
                            "description": {
                                "type": "string",
                                "description": "New description (optional)"
                            },
                            "tags": {
                                "type": "string",
                                "description": "New comma-separated tags (optional)"
                            },
                            "publish": {
                                "type": "boolean",
                                "description": "New publish status (optional)"
                            }
                        },
                        "required": ["page_id"]
                    }
                ),
                Tool(
                    name="list_pages",
                    description="List pages under a specific path",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "path_prefix": {
                                "type": "string",
                                "default": "",
                                "description": "Path prefix to filter by"
                            }
                        }
                    }
                ),
                Tool(
                    name="create_lesson",
                    description="Create a lessons learned entry to prevent repeating mistakes",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "title": {
                                "type": "string",
                                "description": "Lesson title (e.g., 'Sprint 16 - Prevent Infinite Loops')"
                            },
                            "content": {
                                "type": "string",
                                "description": "Lesson content (markdown with problem, solution, prevention)"
                            },
                            "tags": {
                                "type": "string",
                                "description": "Comma-separated tags for categorization"
                            },
                            "category": {
                                "type": "string",
                                "default": "sprints",
                                "description": "Category (sprints, patterns, architecture, etc.)"
                            }
                        },
                        "required": ["title", "content", "tags"]
                    }
                ),
                Tool(
                    name="search_lessons",
                    description="Search lessons learned from previous sprints to avoid known pitfalls",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "query": {
                                "type": "string",
                                "description": "Search query (optional)"
                            },
                            "tags": {
                                "type": "string",
                                "description": "Comma-separated tags to filter by (optional)"
                            },
                            "limit": {
                                "type": "integer",
                                "default": 20,
                                "description": "Maximum results"
                            }
                        }
                    }
                ),
                Tool(
                    name="tag_lesson",
                    description="Add or update tags on a lessons learned entry",
                    inputSchema={
                        "type": "object",
                        "properties": {
                            "page_id": {
                                "type": "integer",
                                "description": "Lesson page ID"
                            },
                            "tags": {
                                "type": "string",
                                "description": "Comma-separated tags"
                            }
                        },
                        "required": ["page_id", "tags"]
                    }
                )
            ]
        @self.server.call_tool()
        async def call_tool(name: str, arguments: dict) -> list[TextContent]:
            """
            Handle tool invocation.
            Args:
                name: Tool name
                arguments: Tool arguments
            Returns:
                List of TextContent with results
            """
            try:
                # Route to appropriate client method
                if name == "search_pages":
                    tags = arguments.get('tags')
                    tag_list = [t.strip() for t in tags.split(',')] if tags else None
                    results = await self.client.search_pages(
                        query=arguments['query'],
                        tags=tag_list,
                        limit=arguments.get('limit', 20)
                    )
                    result = {'success': True, 'count': len(results), 'pages': results}
                elif name == "get_page":
                    page = await self.client.get_page(arguments['path'])
                    if page:
                        result = {'success': True, 'page': page}
                    else:
                        result = {'success': False, 'error': f"Page not found: {arguments['path']}"}
                elif name == "create_page":
                    tags = arguments.get('tags')
                    tag_list = [t.strip() for t in tags.split(',')] if tags else []
                    page = await self.client.create_page(
                        path=arguments['path'],
                        title=arguments['title'],
                        content=arguments['content'],
                        description=arguments.get('description', ''),
                        tags=tag_list,
                        is_published=arguments.get('publish', True)
                    )
                    result = {'success': True, 'page': page}
                elif name == "update_page":
                    tags = arguments.get('tags')
                    tag_list = [t.strip() for t in tags.split(',')] if tags else None
                    page = await self.client.update_page(
                        page_id=arguments['page_id'],
                        content=arguments.get('content'),
                        title=arguments.get('title'),
                        description=arguments.get('description'),
                        tags=tag_list,
                        is_published=arguments.get('publish')
                    )
                    result = {'success': True, 'page': page}
                elif name == "list_pages":
                    pages = await self.client.list_pages(
                        path_prefix=arguments.get('path_prefix', '')
                    )
                    result = {'success': True, 'count': len(pages), 'pages': pages}
                elif name == "create_lesson":
                    tag_list = [t.strip() for t in arguments['tags'].split(',')]
                    lesson = await self.client.create_lesson(
                        title=arguments['title'],
                        content=arguments['content'],
                        tags=tag_list,
                        category=arguments.get('category', 'sprints')
                    )
                    result = {
                        'success': True,
                        'lesson': lesson,
                        'message': f"Lesson learned captured: {arguments['title']}"
                    }
                elif name == "search_lessons":
                    tags = arguments.get('tags')
                    tag_list = [t.strip() for t in tags.split(',')] if tags else None
                    lessons = await self.client.search_lessons(
                        query=arguments.get('query'),
                        tags=tag_list,
                        limit=arguments.get('limit', 20)
                    )
                    result = {
                        'success': True,
                        'count': len(lessons),
                        'lessons': lessons,
                        'message': f"Found {len(lessons)} relevant lessons"
                    }
                elif name == "tag_lesson":
                    tag_list = [t.strip() for t in arguments['tags'].split(',')]
                    lesson = await self.client.tag_lesson(
                        page_id=arguments['page_id'],
                        new_tags=tag_list
                    )
                    result = {'success': True, 'lesson': lesson, 'message': 'Tags updated'}
                else:
                    raise ValueError(f"Unknown tool: {name}")
                return [TextContent(
                    type="text",
                    text=json.dumps(result, indent=2)
                )]
            except Exception as e:
                logger.error(f"Tool {name} failed: {e}")
                return [TextContent(
                    type="text",
                    text=json.dumps({'success': False, 'error': str(e)}, indent=2)
                )]
    async def run(self):
        """Run the MCP server"""
        await self.initialize()
        self.setup_tools()
        async with stdio_server() as (read_stream, write_stream):
            await self.server.run(
                read_stream,
                write_stream,
                self.server.create_initialization_options()
            )
 async def main():
    """Main entry point"""
    server = WikiJSMCPServer()
    await server.run()
 if __name__ == "__main__":
    asyncio.run(main())
--- a/plugins/projman/mcp-servers/wikijs/mcp_server/tools/init.py
+++ b/plugins/projman/mcp-servers/wikijs/mcp_server/tools/init.py
@@ -1 +0,0 @@
 """Wiki.js MCP tools."""
--- a/plugins/projman/mcp-servers/wikijs/mcp_server/tools/lessons_learned.py
+++ b/plugins/projman/mcp-servers/wikijs/mcp_server/tools/lessons_learned.py
@@ -1,183 +0,0 @@
 """
 MCP tools for Wiki.js lessons learned management.
 """
 from typing import Dict, Any, List, Optional
 from mcp.server import Tool
 from ..wikijs_client import WikiJSClient
 import logging
 logger = logging.getLogger(__name__)
 def create_lesson_tools(client: WikiJSClient) -> List[Tool]:
    """
    Create MCP tools for lessons learned management.
    Args:
        client: WikiJSClient instance
    Returns:
        List of MCP tools
    """
    async def create_lesson(
        title: str,
        content: str,
        tags: str,
        category: str = "sprints"
    ) -> Dict[str, Any]:
        """
        Create a lessons learned entry.
        After 15 sprints without systematic lesson capture, repeated mistakes occurred.
        This tool ensures lessons are captured and searchable for future sprints.
        Args:
            title: Lesson title (e.g., "Sprint 16 - Claude Code Infinite Loop on Label Validation")
            content: Lesson content in markdown (problem, solution, prevention)
            tags: Comma-separated tags (e.g., "claude-code, testing, labels, validation")
            category: Category for organization (default: "sprints", also: "patterns", "architecture")
        Returns:
            Created lesson page data
        Example:
            create_lesson(
                title="Sprint 16 - Prevent Infinite Loops in Validation",
                content="## Problem\\n\\nClaude Code entered infinite loop...\\n\\n## Solution\\n\\n...",
                tags="claude-code, testing, infinite-loop, validation",
                category="sprints"
            )
        """
        try:
            tag_list = [t.strip() for t in tags.split(',')]
            lesson = await client.create_lesson(
                title=title,
                content=content,
                tags=tag_list,
                category=category
            )
            return {
                'success': True,
                'lesson': lesson,
                'message': f'Lesson learned captured: {title}'
            }
        except Exception as e:
            logger.error(f"Error creating lesson: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    async def search_lessons(
        query: Optional[str] = None,
        tags: Optional[str] = None,
        limit: int = 20
    ) -> Dict[str, Any]:
        """
        Search lessons learned entries.
        Use this at sprint start to find relevant lessons from previous sprints.
        Prevents repeating the same mistakes.
        Args:
            query: Search query (e.g., "validation", "infinite loop", "docker")
            tags: Comma-separated tags to filter by (e.g., "claude-code, testing")
            limit: Maximum number of results (default: 20)
        Returns:
            List of matching lessons learned
        Example:
            # Before implementing validation logic
            search_lessons(query="validation", tags="testing, claude-code")
            # Before working with Docker
            search_lessons(query="docker", tags="deployment")
        """
        try:
            tag_list = [t.strip() for t in tags.split(',')] if tags else None
            lessons = await client.search_lessons(
                query=query,
                tags=tag_list,
                limit=limit
            )
            return {
                'success': True,
                'count': len(lessons),
                'lessons': lessons,
                'message': f'Found {len(lessons)} relevant lessons'
            }
        except Exception as e:
            logger.error(f"Error searching lessons: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    async def tag_lesson(
        page_id: int,
        tags: str
    ) -> Dict[str, Any]:
        """
        Add or update tags on a lesson.
        Args:
            page_id: Lesson page ID (from create_lesson or search_lessons)
            tags: Comma-separated tags (will replace existing tags)
        Returns:
            Updated lesson data
        """
        try:
            tag_list = [t.strip() for t in tags.split(',')]
            lesson = await client.tag_lesson(
                page_id=page_id,
                new_tags=tag_list
            )
            return {
                'success': True,
                'lesson': lesson,
                'message': 'Tags updated successfully'
            }
        except Exception as e:
            logger.error(f"Error tagging lesson: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    # Define MCP tools
    tools = [
        Tool(
            name="create_lesson",
            description=(
                "Create a lessons learned entry to prevent repeating mistakes. "
                "Critical for capturing sprint insights, architectural decisions, "
                "and technical gotchas for future reference."
            ),
            function=create_lesson
        ),
        Tool(
            name="search_lessons",
            description=(
                "Search lessons learned from previous sprints and projects. "
                "Use this before starting new work to avoid known pitfalls and "
                "leverage past solutions."
            ),
            function=search_lessons
        ),
        Tool(
            name="tag_lesson",
            description="Add or update tags on a lessons learned entry for better categorization",
            function=tag_lesson
        )
    ]
    return tools
--- a/plugins/projman/mcp-servers/wikijs/mcp_server/tools/pages.py
+++ b/plugins/projman/mcp-servers/wikijs/mcp_server/tools/pages.py
@@ -1,229 +0,0 @@
 """
 MCP tools for Wiki.js page management.
 """
 from typing import Dict, Any, List, Optional
 from mcp.server import Tool
 from ..wikijs_client import WikiJSClient
 import logging
 logger = logging.getLogger(__name__)
 def create_page_tools(client: WikiJSClient) -> List[Tool]:
    """
    Create MCP tools for page management.
    Args:
        client: WikiJSClient instance
    Returns:
        List of MCP tools
    """
    async def search_pages(
        query: str,
        tags: Optional[str] = None,
        limit: int = 20
    ) -> Dict[str, Any]:
        """
        Search Wiki.js pages by keywords and tags.
        Args:
            query: Search query string
            tags: Comma-separated list of tags to filter by
            limit: Maximum number of results (default: 20)
        Returns:
            List of matching pages with path, title, description, and tags
        """
        try:
            tag_list = [t.strip() for t in tags.split(',')] if tags else None
            results = await client.search_pages(query, tag_list, limit)
            return {
                'success': True,
                'count': len(results),
                'pages': results
            }
        except Exception as e:
            logger.error(f"Error searching pages: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    async def get_page(path: str) -> Dict[str, Any]:
        """
        Get a specific page by path.
        Args:
            path: Page path (can be relative to project or absolute)
        Returns:
            Page data including content, metadata, and tags
        """
        try:
            page = await client.get_page(path)
            if page:
                return {
                    'success': True,
                    'page': page
                }
            else:
                return {
                    'success': False,
                    'error': f'Page not found: {path}'
                }
        except Exception as e:
            logger.error(f"Error getting page: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    async def create_page(
        path: str,
        title: str,
        content: str,
        description: str = "",
        tags: Optional[str] = None,
        publish: bool = True
    ) -> Dict[str, Any]:
        """
        Create a new Wiki.js page.
        Args:
            path: Page path relative to project/base (e.g., 'documentation/api')
            title: Page title
            content: Page content in markdown format
            description: Page description (optional)
            tags: Comma-separated list of tags (optional)
            publish: Whether to publish immediately (default: True)
        Returns:
            Created page data
        """
        try:
            tag_list = [t.strip() for t in tags.split(',')] if tags else []
            page = await client.create_page(
                path=path,
                title=title,
                content=content,
                description=description,
                tags=tag_list,
                is_published=publish
            )
            return {
                'success': True,
                'page': page
            }
        except Exception as e:
            logger.error(f"Error creating page: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    async def update_page(
        page_id: int,
        content: Optional[str] = None,
        title: Optional[str] = None,
        description: Optional[str] = None,
        tags: Optional[str] = None,
        publish: Optional[bool] = None
    ) -> Dict[str, Any]:
        """
        Update an existing Wiki.js page.
        Args:
            page_id: Page ID (from get_page or search_pages)
            content: New content (optional)
            title: New title (optional)
            description: New description (optional)
            tags: New comma-separated tags (optional)
            publish: New publish status (optional)
        Returns:
            Updated page data
        """
        try:
            tag_list = [t.strip() for t in tags.split(',')] if tags else None
            page = await client.update_page(
                page_id=page_id,
                content=content,
                title=title,
                description=description,
                tags=tag_list,
                is_published=publish
            )
            return {
                'success': True,
                'page': page
            }
        except Exception as e:
            logger.error(f"Error updating page: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    async def list_pages(path_prefix: str = "") -> Dict[str, Any]:
        """
        List pages under a specific path.
        Args:
            path_prefix: Path prefix to filter by (relative to project/base)
        Returns:
            List of pages under the specified path
        """
        try:
            pages = await client.list_pages(path_prefix)
            return {
                'success': True,
                'count': len(pages),
                'pages': pages
            }
        except Exception as e:
            logger.error(f"Error listing pages: {e}")
            return {
                'success': False,
                'error': str(e)
            }
    # Define MCP tools
    tools = [
        Tool(
            name="search_pages",
            description="Search Wiki.js pages by keywords and tags",
            function=search_pages
        ),
        Tool(
            name="get_page",
            description="Get a specific Wiki.js page by path",
            function=get_page
        ),
        Tool(
            name="create_page",
            description="Create a new Wiki.js page with content and metadata",
            function=create_page
        ),
        Tool(
            name="update_page",
            description="Update an existing Wiki.js page",
            function=update_page
        ),
        Tool(
            name="list_pages",
            description="List pages under a specific path",
            function=list_pages
        )
    ]
    return tools
--- a/plugins/projman/mcp-servers/wikijs/mcp_server/wikijs_client.py
+++ b/plugins/projman/mcp-servers/wikijs/mcp_server/wikijs_client.py
@@ -1,451 +0,0 @@
 """
 Wiki.js GraphQL API Client.
 Provides methods for interacting with Wiki.js GraphQL API for page management,
 lessons learned, and documentation.
 """
 import httpx
 from typing import List, Dict, Optional, Any
 import logging
 logger = logging.getLogger(__name__)
 class WikiJSClient:
    """Client for Wiki.js GraphQL API"""
    def __init__(self, api_url: str, api_token: str, base_path: str, project: Optional[str] = None):
        """
        Initialize Wiki.js client.
        Args:
            api_url: Wiki.js GraphQL API URL (e.g., http://wiki.example.com/graphql)
            api_token: Wiki.js API token
            base_path: Base path in Wiki.js (e.g., /your-org)
            project: Project path (e.g., projects/my-project) for project mode
        """
        self.api_url = api_url
        self.api_token = api_token
        self.base_path = base_path.rstrip('/')
        self.project = project
        self.mode = 'project' if project else 'company'
        self.headers = {
            'Authorization': f'Bearer {api_token}',
            'Content-Type': 'application/json'
        }
    def _get_full_path(self, relative_path: str) -> str:
        """
        Construct full path based on mode.
        Args:
            relative_path: Path relative to project or base
        Returns:
            Full path in Wiki.js
        """
        relative_path = relative_path.lstrip('/')
        if self.mode == 'project' and self.project:
            # Project mode: base_path/project/relative_path
            return f"{self.base_path}/{self.project}/{relative_path}"
        else:
            # Company mode: base_path/relative_path
            return f"{self.base_path}/{relative_path}"
    async def _execute_query(self, query: str, variables: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
        """
        Execute GraphQL query.
        Args:
            query: GraphQL query string
            variables: Query variables
        Returns:
            Response data
        Raises:
            httpx.HTTPError: On HTTP errors
            ValueError: On GraphQL errors
        """
        async with httpx.AsyncClient() as client:
            response = await client.post(
                self.api_url,
                headers=self.headers,
                json={'query': query, 'variables': variables or {}}
            )
            # Log response for debugging
            if response.status_code != 200:
                logger.error(f"HTTP {response.status_code}: {response.text}")
            response.raise_for_status()
            data = response.json()
            if 'errors' in data:
                errors = data['errors']
                error_messages = [err.get('message', str(err)) for err in errors]
                raise ValueError(f"GraphQL errors: {', '.join(error_messages)}")
            return data.get('data', {})
    async def search_pages(
        self,
        query: str,
        tags: Optional[List[str]] = None,
        limit: int = 20
    ) -> List[Dict[str, Any]]:
        """
        Search pages by keywords and tags.
        Args:
            query: Search query string
            tags: Filter by tags
            limit: Maximum results to return
        Returns:
            List of matching pages
        """
        graphql_query = """
        query SearchPages($query: String!) {
          pages {
            search(query: $query) {
              results {
                id
                path
                title
                description
              }
            }
          }
        }
        """
        data = await self._execute_query(graphql_query, {'query': query})
        results = data.get('pages', {}).get('search', {}).get('results', [])
        # Filter by tags if specified
        if tags:
            tags_lower = [t.lower() for t in tags]
            results = [
                r for r in results
                if any(tag.lower() in tags_lower for tag in r.get('tags', []))
            ]
        return results[:limit]
    async def get_page(self, path: str) -> Optional[Dict[str, Any]]:
        """
        Get specific page by path.
        Args:
            path: Page path (can be relative or absolute)
        Returns:
            Page data or None if not found
        """
        # Convert to absolute path
        if not path.startswith(self.base_path):
            path = self._get_full_path(path)
        graphql_query = """
        query GetPage($path: String!) {
          pages {
            single(path: $path) {
              id
              path
              title
              description
              content
              tags
              createdAt
              updatedAt
              author
              isPublished
            }
          }
        }
        """
        try:
            data = await self._execute_query(graphql_query, {'path': path})
            return data.get('pages', {}).get('single')
        except (httpx.HTTPError, ValueError) as e:
            logger.warning(f"Page not found at {path}: {e}")
            return None
    async def create_page(
        self,
        path: str,
        title: str,
        content: str,
        description: str = "",
        tags: Optional[List[str]] = None,
        is_published: bool = True
    ) -> Dict[str, Any]:
        """
        Create new page.
        Args:
            path: Page path (relative to project/base)
            title: Page title
            content: Page content (markdown)
            description: Page description
            tags: Page tags
            is_published: Whether to publish immediately
        Returns:
            Created page data
        """
        full_path = self._get_full_path(path)
        graphql_query = """
        mutation CreatePage($path: String!, $title: String!, $content: String!, $description: String!, $tags: [String]!, $isPublished: Boolean!, $isPrivate: Boolean!) {
          pages {
            create(
              path: $path
              title: $title
              content: $content
              description: $description
              tags: $tags
              isPublished: $isPublished
              isPrivate: $isPrivate
              editor: "markdown"
              locale: "en"
            ) {
              responseResult {
                succeeded
                errorCode
                slug
                message
              }
              page {
                id
                path
                title
              }
            }
          }
        }
        """
        variables = {
            'path': full_path,
            'title': title,
            'content': content,
            'description': description,
            'tags': tags or [],
            'isPublished': is_published,
            'isPrivate': False  # Default to not private
        }
        data = await self._execute_query(graphql_query, variables)
        result = data.get('pages', {}).get('create', {})
        if not result.get('responseResult', {}).get('succeeded'):
            error_msg = result.get('responseResult', {}).get('message', 'Unknown error')
            raise ValueError(f"Failed to create page: {error_msg}")
        return result.get('page', {})
    async def update_page(
        self,
        page_id: int,
        content: Optional[str] = None,
        title: Optional[str] = None,
        description: Optional[str] = None,
        tags: Optional[List[str]] = None,
        is_published: Optional[bool] = None
    ) -> Dict[str, Any]:
        """
        Update existing page.
        Args:
            page_id: Page ID
            content: New content (if changing)
            title: New title (if changing)
            description: New description (if changing)
            tags: New tags (if changing)
            is_published: New publish status (if changing)
        Returns:
            Updated page data
        """
        # Build update fields dynamically
        fields = []
        variables = {'id': page_id}
        if content is not None:
            fields.append('content: $content')
            variables['content'] = content
        if title is not None:
            fields.append('title: $title')
            variables['title'] = title
        if description is not None:
            fields.append('description: $description')
            variables['description'] = description
        if tags is not None:
            fields.append('tags: $tags')
            variables['tags'] = tags
        if is_published is not None:
            fields.append('isPublished: $isPublished')
            variables['isPublished'] = is_published
        fields_str = ', '.join(fields)
        graphql_query = f"""
        mutation UpdatePage($id: Int!{''.join([f', ${k}: {type(v).__name__.title()}' for k, v in variables.items() if k != 'id'])}) {{
          pages {{
            update(
              id: $id
              {fields_str}
            ) {{
              responseResult {{
                succeeded
                errorCode
                message
              }}
              page {{
                id
                path
                title
                updatedAt
              }}
            }}
          }}
        }}
        """
        data = await self._execute_query(graphql_query, variables)
        result = data.get('pages', {}).get('update', {})
        if not result.get('responseResult', {}).get('succeeded'):
            error_msg = result.get('responseResult', {}).get('message', 'Unknown error')
            raise ValueError(f"Failed to update page: {error_msg}")
        return result.get('page', {})
    async def list_pages(self, path_prefix: str = "") -> List[Dict[str, Any]]:
        """
        List pages under a specific path.
        Args:
            path_prefix: Path prefix to filter (relative to project/base)
        Returns:
            List of pages
        """
        # Construct full path based on mode
        if path_prefix:
            full_path = self._get_full_path(path_prefix)
        else:
            # Empty path_prefix: return all pages in project (project mode) or base (company mode)
            if self.mode == 'project' and self.project:
                full_path = f"{self.base_path}/{self.project}"
            else:
                full_path = self.base_path
        graphql_query = """
        query ListPages {
          pages {
            list {
              id
              path
              title
              description
              tags
              createdAt
              updatedAt
              isPublished
            }
          }
        }
        """
        data = await self._execute_query(graphql_query)
        all_pages = data.get('pages', {}).get('list', [])
        # Filter by path prefix
        if full_path:
            return [p for p in all_pages if p.get('path', '').startswith(full_path)]
        return all_pages
    async def create_lesson(
        self,
        title: str,
        content: str,
        tags: List[str],
        category: str = "sprints"
    ) -> Dict[str, Any]:
        """
        Create a lessons learned entry.
        Args:
            title: Lesson title
            content: Lesson content (markdown)
            tags: Tags for categorization
            category: Category (sprints, patterns, etc.)
        Returns:
            Created lesson page data
        """
        # Construct path: lessons-learned/category/title-slug
        slug = title.lower().replace(' ', '-').replace('_', '-')
        path = f"lessons-learned/{category}/{slug}"
        return await self.create_page(
            path=path,
            title=title,
            content=content,
            description=f"Lessons learned: {title}",
            tags=tags + ['lesson-learned', category],
            is_published=True
        )
    async def search_lessons(
        self,
        query: Optional[str] = None,
        tags: Optional[List[str]] = None,
        limit: int = 20
    ) -> List[Dict[str, Any]]:
        """
        Search lessons learned entries.
        Args:
            query: Search query (optional)
            tags: Filter by tags
            limit: Maximum results
        Returns:
            List of matching lessons
        """
        # Search in lessons-learned path
        search_query = query or "lesson"
        results = await self.search_pages(search_query, tags, limit)
        # Filter to only lessons-learned path
        lessons_path = self._get_full_path("lessons-learned")
        return [r for r in results if r.get('path', '').startswith(lessons_path)]
    async def tag_lesson(self, page_id: int, new_tags: List[str]) -> Dict[str, Any]:
        """
        Add tags to a lesson.
        Args:
            page_id: Lesson page ID
            new_tags: Tags to add
        Returns:
            Updated page data
        """
        # Get current page to merge tags
        # For now, just replace tags (can enhance to merge later)
        return await self.update_page(page_id=page_id, tags=new_tags)
--- a/plugins/projman/mcp-servers/wikijs/requirements.txt
+++ b/plugins/projman/mcp-servers/wikijs/requirements.txt
@@ -1,19 +0,0 @@
 # Wiki.js MCP Server Dependencies
 # MCP SDK
 mcp>=0.1.0
 # HTTP client for GraphQL
 httpx>=0.27.0
 httpx-sse>=0.4.0
 # Configuration
 python-dotenv>=1.0.0
 # Testing
 pytest>=8.0.0
 pytest-asyncio>=0.23.0
 pytest-mock>=3.12.0
 # Type hints
 typing-extensions>=4.9.0
--- a/plugins/projman/mcp-servers/wikijs/test_integration.py
+++ b/plugins/projman/mcp-servers/wikijs/test_integration.py
@@ -1,185 +0,0 @@
 #!/usr/bin/env python3
 """
 Integration test script for Wiki.js MCP Server.
 Tests against real Wiki.js instance.
 Usage:
    python test_integration.py
 """
 import asyncio
 import sys
 from mcp_server.config import WikiJSConfig
 from mcp_server.wikijs_client import WikiJSClient
 async def test_connection():
    """Test basic connection to Wiki.js"""
    print("🔌 Testing Wiki.js connection...")
    try:
        config_loader = WikiJSConfig()
        config = config_loader.load()
        print(f"✓ Configuration loaded")
        print(f"  - API URL: {config['api_url']}")
        print(f"  - Base Path: {config['base_path']}")
        print(f"  - Mode: {config['mode']}")
        if config.get('project'):
            print(f"  - Project: {config['project']}")
        client = WikiJSClient(
            api_url=config['api_url'],
            api_token=config['api_token'],
            base_path=config['base_path'],
            project=config.get('project')
        )
        print("✓ Client initialized")
        return client
    except Exception as e:
        print(f"✗ Configuration failed: {e}")
        return None
 async def test_list_pages(client):
    """Test listing pages"""
    print("\n📄 Testing list_pages...")
    try:
        pages = await client.list_pages("")
        print(f"✓ Found {len(pages)} pages")
        if pages:
            print(f"  Sample pages:")
            for page in pages[:5]:
                print(f"    - {page.get('title')} ({page.get('path')})")
        return True
    except Exception as e:
        print(f"✗ List pages failed: {e}")
        return False
 async def test_search_pages(client):
    """Test searching pages"""
    print("\n🔍 Testing search_pages...")
    try:
        results = await client.search_pages("test", limit=5)
        print(f"✓ Search returned {len(results)} results")
        if results:
            print(f"  Sample results:")
            for result in results[:3]:
                print(f"    - {result.get('title')}")
        return True
    except Exception as e:
        print(f"✗ Search failed: {e}")
        return False
 async def test_create_page(client):
    """Test creating a page"""
    print("\n➕ Testing create_page...")
    # Use timestamp to create unique page path
    import time
    timestamp = int(time.time())
    page_path = f"testing/integration-test-{timestamp}"
    try:
        page = await client.create_page(
            path=page_path,
            title=f"Integration Test Page - {timestamp}",
            content="# Integration Test\n\nThis page was created by the Wiki.js MCP Server integration test.",
            description="Automated test page",
            tags=["test", "integration", "mcp"],
            is_published=False  # Don't publish test page
        )
        print(f"✓ Page created successfully")
        print(f"  - ID: {page.get('id')}")
        print(f"  - Path: {page.get('path')}")
        print(f"  - Title: {page.get('title')}")
        return page_path  # Return path for testing get_page
    except Exception as e:
        import traceback
        print(f"✗ Create page failed: {e}")
        print(f"  Error details: {traceback.format_exc()}")
        return None
 async def test_get_page(client, page_path):
    """Test getting a specific page"""
    print("\n📖 Testing get_page...")
    try:
        page = await client.get_page(page_path)
        if page:
            print(f"✓ Page retrieved successfully")
            print(f"  - Title: {page.get('title')}")
            print(f"  - Tags: {', '.join(page.get('tags', []))}")
            print(f"  - Published: {page.get('isPublished')}")
            return True
        else:
            print(f"✗ Page not found: {page_path}")
            return False
    except Exception as e:
        print(f"✗ Get page failed: {e}")
        return False
 async def main():
    """Run all integration tests"""
    print("=" * 60)
    print("Wiki.js MCP Server - Integration Tests")
    print("=" * 60)
    # Test connection
    client = await test_connection()
    if not client:
        print("\n❌ Integration tests failed: Cannot connect to Wiki.js")
        sys.exit(1)
    # Run tests
    results = []
    results.append(await test_list_pages(client))
    results.append(await test_search_pages(client))
    page_path = await test_create_page(client)
    if page_path:
        results.append(True)
        # Test getting the created page
        results.append(await test_get_page(client, page_path))
    else:
        results.append(False)
        results.append(False)
    # Summary
    print("\n" + "=" * 60)
    print("Test Summary")
    print("=" * 60)
    passed = sum(results)
    total = len(results)
    print(f"✓ Passed: {passed}/{total}")
    print(f"✗ Failed: {total - passed}/{total}")
    if passed == total:
        print("\n✅ All integration tests passed!")
        sys.exit(0)
    else:
        print("\n❌ Some integration tests failed")
        sys.exit(1)
 if __name__ == "__main__":
    asyncio.run(main())
--- a/plugins/projman/mcp-servers/wikijs/tests/init.py
+++ b/plugins/projman/mcp-servers/wikijs/tests/init.py
@@ -1 +0,0 @@
 """Tests for Wiki.js MCP Server."""
--- a/plugins/projman/mcp-servers/wikijs/tests/test_config.py
+++ b/plugins/projman/mcp-servers/wikijs/tests/test_config.py
@@ -1,109 +0,0 @@
 """
 Tests for WikiJS configuration loader.
 """
 import pytest
 from pathlib import Path
 from unittest.mock import patch, MagicMock
 from mcp_server.config import WikiJSConfig
@pytest.fixture
 def mock_env(monkeypatch, tmp_path):
    """Mock environment with temporary config files"""
    # Create mock system config
    system_config = tmp_path / ".config" / "claude" / "wikijs.env"
    system_config.parent.mkdir(parents=True)
    system_config.write_text(
        "WIKIJS_API_URL=http://wiki.test.com/graphql\n"
        "WIKIJS_API_TOKEN=test_token_123\n"
        "WIKIJS_BASE_PATH=/test-company\n"
    )
    # Mock Path.home()
    with patch('pathlib.Path.home', return_value=tmp_path):
        yield tmp_path
 def test_load_system_config(mock_env):
    """Test loading system-level configuration"""
    config = WikiJSConfig()
    result = config.load()
    assert result['api_url'] == "http://wiki.test.com/graphql"
    assert result['api_token'] == "test_token_123"
    assert result['base_path'] == "/test-company"
    assert result['project'] is None
    assert result['mode'] == 'company'  # No project = company mode
 def test_project_config_override(mock_env, tmp_path, monkeypatch):
    """Test project-level config overrides system-level"""
    # Create project-level config
    project_config = tmp_path / ".env"
    project_config.write_text(
        "WIKIJS_PROJECT=projects/test-project\n"
    )
    # Mock Path.cwd()
    monkeypatch.setattr('pathlib.Path.cwd', lambda: tmp_path)
    config = WikiJSConfig()
    result = config.load()
    assert result['api_url'] == "http://wiki.test.com/graphql"  # From system
    assert result['project'] == "projects/test-project"  # From project
    assert result['mode'] == 'project'  # Has project = project mode
 def test_missing_system_config():
    """Test error when system config is missing"""
    with patch('pathlib.Path.home', return_value=Path('/nonexistent')):
        config = WikiJSConfig()
        with pytest.raises(FileNotFoundError, match="System config not found"):
            config.load()
 def test_missing_required_config(mock_env, monkeypatch):
    """Test validation of required configuration"""
    # Clear environment variables from previous tests
    monkeypatch.delenv('WIKIJS_API_URL', raising=False)
    monkeypatch.delenv('WIKIJS_API_TOKEN', raising=False)
    monkeypatch.delenv('WIKIJS_BASE_PATH', raising=False)
    monkeypatch.delenv('WIKIJS_PROJECT', raising=False)
    # Create incomplete system config
    system_config = mock_env / ".config" / "claude" / "wikijs.env"
    system_config.write_text(
        "WIKIJS_API_URL=http://wiki.test.com/graphql\n"
        # Missing API_TOKEN and BASE_PATH
    )
    config = WikiJSConfig()
    with pytest.raises(ValueError, match="Missing required configuration"):
        config.load()
 def test_mode_detection_project(mock_env, tmp_path, monkeypatch):
    """Test mode detection when WIKIJS_PROJECT is set"""
    project_config = tmp_path / ".env"
    project_config.write_text("WIKIJS_PROJECT=projects/my-project\n")
    monkeypatch.setattr('pathlib.Path.cwd', lambda: tmp_path)
    config = WikiJSConfig()
    result = config.load()
    assert result['mode'] == 'project'
    assert result['project'] == 'projects/my-project'
 def test_mode_detection_company(mock_env, monkeypatch):
    """Test mode detection when WIKIJS_PROJECT is not set (company mode)"""
    # Clear WIKIJS_PROJECT from environment
    monkeypatch.delenv('WIKIJS_PROJECT', raising=False)
    config = WikiJSConfig()
    result = config.load()
    assert result['mode'] == 'company'
    assert result['project'] is None
--- a/plugins/projman/mcp-servers/wikijs/tests/test_wikijs_client.py
+++ b/plugins/projman/mcp-servers/wikijs/tests/test_wikijs_client.py
@@ -1,355 +0,0 @@
 """
 Tests for Wiki.js GraphQL client.
 """
 import pytest
 from unittest.mock import AsyncMock, patch, MagicMock
 from mcp_server.wikijs_client import WikiJSClient
@pytest.fixture
 def client():
    """Create WikiJSClient instance for testing"""
    return WikiJSClient(
        api_url="http://wiki.test.com/graphql",
        api_token="test_token_123",
        base_path="/test-company",
        project="projects/test-project"
    )
@pytest.fixture
 def company_client():
    """Create WikiJSClient in company mode"""
    return WikiJSClient(
        api_url="http://wiki.test.com/graphql",
        api_token="test_token_123",
        base_path="/test-company",
        project=None  # Company mode
    )
 def test_client_initialization(client):
    """Test client initializes with correct settings"""
    assert client.api_url == "http://wiki.test.com/graphql"
    assert client.api_token == "test_token_123"
    assert client.base_path == "/test-company"
    assert client.project == "projects/test-project"
    assert client.mode == 'project'
 def test_company_mode_initialization(company_client):
    """Test client initializes in company mode"""
    assert company_client.mode == 'company'
    assert company_client.project is None
 def test_get_full_path_project_mode(client):
    """Test path construction in project mode"""
    path = client._get_full_path("documentation/api")
    assert path == "/test-company/projects/test-project/documentation/api"
 def test_get_full_path_company_mode(company_client):
    """Test path construction in company mode"""
    path = company_client._get_full_path("shared/architecture")
    assert path == "/test-company/shared/architecture"
@pytest.mark.asyncio
 async def test_search_pages(client):
    """Test searching pages"""
    mock_response = {
        'data': {
            'pages': {
                'search': {
                    'results': [
                        {
                            'id': 1,
                            'path': '/test-company/projects/test-project/doc1',
                            'title': 'Document 1',
                            'tags': ['api', 'documentation']
                        },
                        {
                            'id': 2,
                            'path': '/test-company/projects/test-project/doc2',
                            'title': 'Document 2',
                            'tags': ['guide', 'tutorial']
                        }
                    ]
                }
            }
        }
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        results = await client.search_pages("documentation")
        assert len(results) == 2
        assert results[0]['title'] == 'Document 1'
@pytest.mark.asyncio
 async def test_get_page(client):
    """Test getting a specific page"""
    mock_response = {
        'data': {
            'pages': {
                'single': {
                    'id': 1,
                    'path': '/test-company/projects/test-project/doc1',
                    'title': 'Document 1',
                    'content': '# Test Content',
                    'tags': ['api'],
                    'isPublished': True
                }
            }
        }
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        page = await client.get_page("doc1")
        assert page is not None
        assert page['title'] == 'Document 1'
        assert page['content'] == '# Test Content'
@pytest.mark.asyncio
 async def test_create_page(client):
    """Test creating a new page"""
    mock_response = {
        'data': {
            'pages': {
                'create': {
                    'responseResult': {
                        'succeeded': True,
                        'errorCode': None,
                        'message': 'Page created successfully'
                    },
                    'page': {
                        'id': 1,
                        'path': '/test-company/projects/test-project/new-doc',
                        'title': 'New Document'
                    }
                }
            }
        }
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        page = await client.create_page(
            path="new-doc",
            title="New Document",
            content="# Content",
            tags=["test"]
        )
        assert page['id'] == 1
        assert page['title'] == 'New Document'
@pytest.mark.asyncio
 async def test_update_page(client):
    """Test updating a page"""
    mock_response = {
        'data': {
            'pages': {
                'update': {
                    'responseResult': {
                        'succeeded': True,
                        'message': 'Page updated'
                    },
                    'page': {
                        'id': 1,
                        'path': '/test-company/projects/test-project/doc1',
                        'title': 'Updated Title'
                    }
                }
            }
        }
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        page = await client.update_page(
            page_id=1,
            title="Updated Title"
        )
        assert page['title'] == 'Updated Title'
@pytest.mark.asyncio
 async def test_list_pages(client):
    """Test listing pages"""
    mock_response = {
        'data': {
            'pages': {
                'list': [
                    {'id': 1, 'path': '/test-company/projects/test-project/doc1', 'title': 'Doc 1'},
                    {'id': 2, 'path': '/test-company/projects/test-project/doc2', 'title': 'Doc 2'},
                    {'id': 3, 'path': '/test-company/other-project/doc3', 'title': 'Doc 3'}
                ]
            }
        }
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        # List all pages in current project
        pages = await client.list_pages("")
        # Should only return pages from test-project
        assert len(pages) == 2
@pytest.mark.asyncio
 async def test_create_lesson(client):
    """Test creating a lesson learned"""
    mock_response = {
        'data': {
            'pages': {
                'create': {
                    'responseResult': {
                        'succeeded': True,
                        'message': 'Lesson created'
                    },
                    'page': {
                        'id': 1,
                        'path': '/test-company/projects/test-project/lessons-learned/sprints/test-lesson',
                        'title': 'Test Lesson'
                    }
                }
            }
        }
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        lesson = await client.create_lesson(
            title="Test Lesson",
            content="# Lesson Content",
            tags=["testing", "sprint-16"],
            category="sprints"
        )
        assert lesson['id'] == 1
        assert 'lessons-learned' in lesson['path']
@pytest.mark.asyncio
 async def test_search_lessons(client):
    """Test searching lessons learned"""
    mock_response = {
        'data': {
            'pages': {
                'search': {
                    'results': [
                        {
                            'id': 1,
                            'path': '/test-company/projects/test-project/lessons-learned/sprints/lesson1',
                            'title': 'Lesson 1',
                            'tags': ['testing']
                        },
                        {
                            'id': 2,
                            'path': '/test-company/projects/test-project/documentation/doc1',
                            'title': 'Doc 1',
                            'tags': ['guide']
                        }
                    ]
                }
            }
        }
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        lessons = await client.search_lessons(query="testing")
        # Should only return lessons-learned pages
        assert len(lessons) == 1
        assert 'lessons-learned' in lessons[0]['path']
@pytest.mark.asyncio
 async def test_graphql_error_handling(client):
    """Test handling of GraphQL errors"""
    mock_response = {
        'errors': [
            {'message': 'Page not found'},
            {'message': 'Invalid query'}
        ]
    }
    with patch('httpx.AsyncClient') as mock_client:
        mock_instance = MagicMock()
        mock_instance.__aenter__.return_value = mock_instance
        mock_instance.__aexit__.return_value = None
        mock_instance.post = AsyncMock(return_value=MagicMock(
            json=lambda: mock_response,
            raise_for_status=lambda: None
        ))
        mock_client.return_value = mock_instance
        with pytest.raises(ValueError, match="GraphQL errors"):
            await client.search_pages("test")
		`@@ -1,3 +0,0 @@`
			`"""Wiki.js MCP Server for Claude Code."""`

			`__version__ = "0.1.0"`