Merge pull request 'development' (#442 ) from development into main

Reviewed-on: #442
Merge pull request 'fix: audit fixes — metadata.json, stale profiles, canonical paths, validation' (#441 ) from fix/audit-metadata-profiles-validation into development
2026-02-05 02:39:33 +00:00 · 2026-02-05 02:39:17 +00:00 · 2026-02-04 21:36:49 -05:00 · 2026-02-04 23:13:00 +00:00 · 2026-02-04 23:12:46 +00:00 · 2026-02-04 18:11:43 -05:00
35 changed files with 887 additions and 88 deletions
--- a/.claude-plugin/marketplace-full.json
+++ b/.claude-plugin/marketplace-full.json
@@ -0,0 +1,205 @@
+{
+  "name": "leo-claude-mktplace",
+  "owner": {
+    "name": "Leo Miranda",
+    "email": "leobmiranda@gmail.com"
+  },
+  "metadata": {
+    "description": "Project management plugins with Gitea and NetBox integrations",
+    "version": "7.1.0"
+  },
+  "plugins": [
+    {
+      "name": "projman",
+      "version": "7.1.0",
+      "description": "Sprint planning and project management with Gitea integration",
+      "source": "./plugins/projman",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/projman/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["sprint", "agile", "gitea", "project-management"],
+      "license": "MIT"
+    },
+    {
+      "name": "doc-guardian",
+      "version": "7.1.0",
+      "description": "Automatic documentation drift detection and synchronization",
+      "source": "./plugins/doc-guardian",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/doc-guardian/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "productivity",
+      "tags": ["documentation", "drift-detection", "sync"],
+      "license": "MIT"
+    },
+    {
+      "name": "code-sentinel",
+      "version": "7.1.0",
+      "description": "Security scanning and code refactoring tools",
+      "source": "./plugins/code-sentinel",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/code-sentinel/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "security",
+      "tags": ["security-scan", "refactoring", "vulnerabilities"],
+      "license": "MIT"
+    },
+    {
+      "name": "project-hygiene",
+      "version": "7.1.0",
+      "description": "Post-task cleanup hook that removes temp files and manages orphaned files",
+      "source": "./plugins/project-hygiene",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/project-hygiene/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "productivity",
+      "tags": ["cleanup", "automation", "hygiene"],
+      "license": "MIT"
+    },
+    {
+      "name": "cmdb-assistant",
+      "version": "7.1.0",
+      "description": "NetBox CMDB integration with data quality validation and machine registration",
+      "source": "./plugins/cmdb-assistant",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/cmdb-assistant/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "infrastructure",
+      "tags": ["cmdb", "netbox", "dcim", "ipam", "data-quality", "validation"],
+      "license": "MIT"
+    },
+    {
+      "name": "claude-config-maintainer",
+      "version": "7.1.0",
+      "description": "CLAUDE.md and settings.local.json optimization for Claude Code projects",
+      "source": "./plugins/claude-config-maintainer",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/claude-config-maintainer/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["claude-md", "configuration", "optimization"],
+      "license": "MIT"
+    },
+    {
+      "name": "clarity-assist",
+      "version": "7.1.0",
+      "description": "Prompt optimization and requirement clarification with ND-friendly accommodations",
+      "source": "./plugins/clarity-assist",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/clarity-assist/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "productivity",
+      "tags": ["prompts", "requirements", "clarification", "nd-friendly"],
+      "license": "MIT"
+    },
+    {
+      "name": "git-flow",
+      "version": "7.1.0",
+      "description": "Git workflow automation with intelligent commit messages and branch management",
+      "source": "./plugins/git-flow",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/git-flow/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["git", "workflow", "commits", "branching"],
+      "license": "MIT"
+    },
+    {
+      "name": "pr-review",
+      "version": "7.1.0",
+      "description": "Multi-agent pull request review with confidence scoring and actionable feedback",
+      "source": "./plugins/pr-review",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/pr-review/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["code-review", "pull-requests", "security", "quality"],
+      "license": "MIT"
+    },
+    {
+      "name": "data-platform",
+      "version": "7.1.0",
+      "description": "Data engineering tools with pandas, PostgreSQL/PostGIS, and dbt integration",
+      "source": "./plugins/data-platform",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/data-platform/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "data",
+      "tags": ["pandas", "postgresql", "postgis", "dbt", "data-engineering", "etl"],
+      "license": "MIT"
+    },
+    {
+      "name": "viz-platform",
+      "version": "7.1.0",
+      "description": "Visualization tools with Dash Mantine Components validation, Plotly charts, and theming",
+      "source": "./plugins/viz-platform",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/viz-platform/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "visualization",
+      "tags": ["dash", "plotly", "mantine", "charts", "dashboards", "theming", "dmc"],
+      "license": "MIT"
+    },
+    {
+      "name": "contract-validator",
+      "version": "7.1.0",
+      "description": "Cross-plugin compatibility validation and Claude.md agent verification",
+      "source": "./plugins/contract-validator",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/contract-validator/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["validation", "contracts", "compatibility", "agents", "interfaces", "cross-plugin"],
+      "license": "MIT"
+    }
+  ]
+}
--- a/.claude-plugin/marketplace-lean.json
+++ b/.claude-plugin/marketplace-lean.json
@@ -0,0 +1,109 @@
+{
+  "name": "leo-claude-mktplace",
+  "owner": {
+    "name": "Leo Miranda",
+    "email": "leobmiranda@gmail.com"
+  },
+  "metadata": {
+    "description": "Project management plugins with Gitea and NetBox integrations",
+    "version": "7.1.0"
+  },
+  "plugins": [
+    {
+      "name": "projman",
+      "version": "7.1.0",
+      "description": "Sprint planning and project management with Gitea integration",
+      "source": "./plugins/projman",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/projman/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["sprint", "agile", "gitea", "project-management"],
+      "license": "MIT"
+    },
+    {
+      "name": "git-flow",
+      "version": "7.1.0",
+      "description": "Git workflow automation with intelligent commit messages and branch management",
+      "source": "./plugins/git-flow",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/git-flow/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["git", "workflow", "commits", "branching"],
+      "license": "MIT"
+    },
+    {
+      "name": "pr-review",
+      "version": "7.1.0",
+      "description": "Multi-agent pull request review with confidence scoring and actionable feedback",
+      "source": "./plugins/pr-review",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/pr-review/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "development",
+      "tags": ["code-review", "pull-requests", "security", "quality"],
+      "license": "MIT"
+    },
+    {
+      "name": "clarity-assist",
+      "version": "7.1.0",
+      "description": "Prompt optimization and requirement clarification with ND-friendly accommodations",
+      "source": "./plugins/clarity-assist",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/clarity-assist/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "productivity",
+      "tags": ["prompts", "requirements", "clarification", "nd-friendly"],
+      "license": "MIT"
+    },
+    {
+      "name": "code-sentinel",
+      "version": "7.1.0",
+      "description": "Security scanning and code refactoring tools",
+      "source": "./plugins/code-sentinel",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/code-sentinel/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "security",
+      "tags": ["security-scan", "refactoring", "vulnerabilities"],
+      "license": "MIT"
+    },
+    {
+      "name": "doc-guardian",
+      "version": "7.1.0",
+      "description": "Automatic documentation drift detection and synchronization",
+      "source": "./plugins/doc-guardian",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/doc-guardian/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "hooks": ["./hooks/hooks.json"],
+      "category": "productivity",
+      "tags": ["documentation", "drift-detection", "sync"],
+      "license": "MIT"
+    }
+  ]
+}
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -6,12 +6,12 @@
  },
  "metadata": {
    "description": "Project management plugins with Gitea and NetBox integrations",
-    "version": "7.0.0"
+    "version": "7.1.0"
  },
  "plugins": [
    {
      "name": "projman",
-      "version": "3.4.0",
+      "version": "7.1.0",
      "description": "Sprint planning and project management with Gitea integration",
      "source": "./plugins/projman",
      "author": {
@@ -27,7 +27,7 @@
    },
    {
      "name": "doc-guardian",
-      "version": "1.1.0",
+      "version": "7.1.0",
      "description": "Automatic documentation drift detection and synchronization",
      "source": "./plugins/doc-guardian",
      "author": {
@@ -43,7 +43,7 @@
    },
    {
      "name": "code-sentinel",
-      "version": "1.0.1",
+      "version": "7.1.0",
      "description": "Security scanning and code refactoring tools",
      "source": "./plugins/code-sentinel",
      "author": {
@@ -59,7 +59,7 @@
    },
    {
      "name": "project-hygiene",
-      "version": "0.1.0",
+      "version": "7.1.0",
      "description": "Post-task cleanup hook that removes temp files and manages orphaned files",
      "source": "./plugins/project-hygiene",
      "author": {
@@ -75,7 +75,7 @@
    },
    {
      "name": "cmdb-assistant",
-      "version": "1.2.0",
+      "version": "7.1.0",
      "description": "NetBox CMDB integration with data quality validation and machine registration",
      "source": "./plugins/cmdb-assistant",
      "author": {
@@ -91,7 +91,7 @@
    },
    {
      "name": "claude-config-maintainer",
-      "version": "1.2.0",
+      "version": "7.1.0",
      "description": "CLAUDE.md and settings.local.json optimization for Claude Code projects",
      "source": "./plugins/claude-config-maintainer",
      "author": {
@@ -107,7 +107,7 @@
    },
    {
      "name": "clarity-assist",
-      "version": "1.2.0",
+      "version": "7.1.0",
      "description": "Prompt optimization and requirement clarification with ND-friendly accommodations",
      "source": "./plugins/clarity-assist",
      "author": {
@@ -123,7 +123,7 @@
    },
    {
      "name": "git-flow",
-      "version": "1.2.0",
+      "version": "7.1.0",
      "description": "Git workflow automation with intelligent commit messages and branch management",
      "source": "./plugins/git-flow",
      "author": {
@@ -139,7 +139,7 @@
    },
    {
      "name": "pr-review",
-      "version": "1.1.0",
+      "version": "7.1.0",
      "description": "Multi-agent pull request review with confidence scoring and actionable feedback",
      "source": "./plugins/pr-review",
      "author": {
@@ -155,7 +155,7 @@
    },
    {
      "name": "data-platform",
-      "version": "1.3.0",
+      "version": "7.1.0",
      "description": "Data engineering tools with pandas, PostgreSQL/PostGIS, and dbt integration",
      "source": "./plugins/data-platform",
      "author": {
@@ -171,7 +171,7 @@
    },
    {
      "name": "viz-platform",
-      "version": "1.1.0",
+      "version": "7.1.0",
      "description": "Visualization tools with Dash Mantine Components validation, Plotly charts, and theming",
      "source": "./plugins/viz-platform",
      "author": {
@@ -187,7 +187,7 @@
    },
    {
      "name": "contract-validator",
-      "version": "1.2.0",
+      "version": "7.1.0",
      "description": "Cross-plugin compatibility validation and Claude.md agent verification",
      "source": "./plugins/contract-validator",
      "author": {
--- a/.gitignore
+++ b/.gitignore
@@ -132,4 +132,5 @@ site/
 *credentials*
 *secret*
 *token*
+!**/token-budget-report.md
 !.gitkeep
--- a/.mcp-full.json
+++ b/.mcp-full.json
@@ -0,0 +1,24 @@
+{
+  "mcpServers": {
+    "gitea": {
+      "command": "./mcp-servers/gitea/run.sh",
+      "args": []
+    },
+    "netbox": {
+      "command": "./mcp-servers/netbox/run.sh",
+      "args": []
+    },
+    "viz-platform": {
+      "command": "./mcp-servers/viz-platform/run.sh",
+      "args": []
+    },
+    "data-platform": {
+      "command": "./mcp-servers/data-platform/run.sh",
+      "args": []
+    },
+    "contract-validator": {
+      "command": "./mcp-servers/contract-validator/run.sh",
+      "args": []
+    }
+  }
+}
--- a/.mcp-lean.json
+++ b/.mcp-lean.json
@@ -0,0 +1,8 @@
+{
+  "mcpServers": {
+    "gitea": {
+      "command": "./mcp-servers/gitea/run.sh",
+      "args": []
+    }
+  }
+}
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,52 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).

 ## [Unreleased]

+### Fixed
+
+- Confirmed projman `metadata.json` exists with gitea MCP mapping
+- Synced `marketplace-full.json` and `marketplace-lean.json` to current version (were stale)
+- Added `metadata.json` validation to `validate-marketplace.sh` — rejects `mcp_servers` in `plugin.json`, verifies MCP server references
+- Updated `CANONICAL-PATHS.md` to current version
+
+### Changed
+
+- Deprecated `switch-profile.sh` in favor of `claude-launch.sh`
+
+---
+
+## [7.1.0] - 2026-02-04
+
+### Added
+
+- **marketplace:** Task-specific launcher script for token optimization
+  - New script: `scripts/claude-launch.sh` loads only needed plugins via `--plugin-dir`
+  - Profiles: sprint (default), review, data, infra, full
+  - Reduces token overhead from ~22K to ~4-6K tokens
+  - Enables `ENABLE_TOOL_SEARCH=true` for MCP lazy loading
+- **marketplace:** Lean/full profile config files for manual switching (superseded by `claude-launch.sh`)
+  - Files: `.mcp-lean.json`, `.mcp-full.json`, `marketplace-lean.json`, `marketplace-full.json`
+  - Script `scripts/switch-profile.sh` available but `claude-launch.sh` is the recommended approach
+  - Full profile remains the default baseline; launcher handles selective loading
+- **projman:** Token usage estimation reporting at sprint workflow boundaries
+  - New skill: `token-budget-report.md` with MCP overhead and skill loading estimation model
+  - Token report displayed at end of `/sprint-plan` and `/sprint-close`
+  - On-demand via `/sprint-status --tokens`
+  - Helps identify which phases and components consume the most context budget
+
+### Changed
+
+- **projman:** `/sprint-status` now uses conditional skill loading for reduced token overhead
+  - Only loads `mcp-tools-reference.md` by default (~1.5k tokens vs ~5k)
+  - `--diagram` flag loads `dependency-management.md` and `progress-tracking.md`
+  - `--tokens` flag loads `token-budget-report.md`
+  - Estimated savings: ~3.5k tokens per status check
+
+### Fixed
+
+- **docs:** Stale command references in data-platform visual-header.md and viz-platform claude-md-integration.md updated to v7.0.0 namespaced names
+- **docs:** git-flow visual-header.md and git-status.md quick actions updated to namespaced commands
+- **docs:** projman/CONFIGURATION.md and docs/DEBUGGING-CHECKLIST.md updated with correct command names
+
 ---

 ## [7.0.0] - 2026-02-03
--- a/README.md
+++ b/README.md
@@ -1,7 +1,32 @@
-# Leo Claude Marketplace - v7.0.0
+# Leo Claude Marketplace - v7.1.0

 A collection of Claude Code plugins for project management, infrastructure automation, and development workflows.

+## Quick Start
+
+Use the launcher script to load only the plugins you need, reducing token overhead from ~22K to ~4-6K tokens:
+
+```bash
+./scripts/claude-launch.sh [profile] [extra-args...]
+```
+
+| Profile | Plugins Loaded | Use Case |
+|---------|----------------|----------|
+| `sprint` | projman, git-flow, pr-review, code-sentinel, doc-guardian, clarity-assist | Default. Sprint planning and development |
+| `review` | pr-review, code-sentinel | Lightweight code review |
+| `data` | data-platform, viz-platform | Data engineering and visualization |
+| `infra` | cmdb-assistant | Infrastructure/CMDB management |
+| `full` | All 12 plugins via marketplace.json | When you need everything |
+
+**Examples:**
+```bash
+./scripts/claude-launch.sh                    # Default sprint profile
+./scripts/claude-launch.sh data --model opus  # Data profile with Opus
+./scripts/claude-launch.sh full               # Load all plugins
+```
+
+The script enables `ENABLE_TOOL_SEARCH=true` for MCP lazy loading.
+
 ## Plugins

 ### Development & Project Management
@@ -22,7 +47,7 @@ AI-guided sprint planning with full Gitea integration. Transforms a proven 15-sp

 **Commands:** `/sprint-plan`, `/sprint-start`, `/sprint-status`, `/sprint-close`, `/labels-sync`, `/pm-setup`, `/pm-review`, `/pm-test`, `/pm-debug`, `/suggest-version`, `/proposal-status`, `/rfc`

-#### [git-flow](./plugins/git-flow) *NEW in v3.0.0*
+#### [git-flow](./plugins/git-flow)
 **Git Workflow Automation**

 Smart git operations with intelligent commit messages and branch management.
@@ -35,7 +60,7 @@ Smart git operations with intelligent commit messages and branch management.

 **Commands:** `/git-commit`, `/git-commit-push`, `/git-commit-merge`, `/git-commit-sync`, `/branch-start`, `/branch-cleanup`, `/git-status`, `/git-config`

-#### [pr-review](./plugins/pr-review) *NEW in v3.0.0*
+#### [pr-review](./plugins/pr-review)
 **Multi-Agent PR Review**

 Comprehensive pull request review using specialized agents.
@@ -54,7 +79,7 @@ Analyze, optimize, and create CLAUDE.md configuration files. Audit and optimize

 **Commands:** `/analyze`, `/optimize`, `/init`, `/config-diff`, `/config-lint`, `/config-audit-settings`, `/config-optimize-settings`, `/config-permissions-map`

-#### [contract-validator](./plugins/contract-validator) *NEW in v5.0.0*
+#### [contract-validator](./plugins/contract-validator)
 **Cross-Plugin Compatibility Validation**

 Validate plugin marketplaces for command conflicts, tool overlaps, and broken agent references.
@@ -69,7 +94,7 @@ Validate plugin marketplaces for command conflicts, tool overlaps, and broken ag

 ### Productivity

-#### [clarity-assist](./plugins/clarity-assist) *NEW in v3.0.0*
+#### [clarity-assist](./plugins/clarity-assist)
 **Prompt Optimization with ND Accommodations**

 Transform vague requests into clear specifications using structured methodology.
@@ -112,7 +137,7 @@ Full CRUD operations for network infrastructure management directly from Claude

 ### Data Engineering

-#### [data-platform](./plugins/data-platform) *NEW in v4.0.0*
+#### [data-platform](./plugins/data-platform)
 **pandas, PostgreSQL/PostGIS, and dbt Integration**

 Comprehensive data engineering toolkit with persistent DataFrame storage.
@@ -127,7 +152,7 @@ Comprehensive data engineering toolkit with persistent DataFrame storage.

 ### Visualization

-#### [viz-platform](./plugins/viz-platform) *NEW in v4.0.0*
+#### [viz-platform](./plugins/viz-platform)
 **Dash Mantine Components Validation and Theming**

 Visualization toolkit with version-locked component validation and design token theming.
@@ -171,7 +196,7 @@ Full Gitea API integration for project management.
 | Wiki | `list_wiki_pages`, `get_wiki_page`, `create_wiki_page`, `update_wiki_page`, `create_lesson`, `search_lessons` |
 | Milestones | `list_milestones`, `get_milestone`, `create_milestone`, `update_milestone`, `delete_milestone` |
 | Dependencies | `list_issue_dependencies`, `create_issue_dependency`, `remove_issue_dependency`, `get_execution_order` |
-| **Pull Requests** | `list_pull_requests`, `get_pull_request`, `get_pr_diff`, `get_pr_comments`, `create_pr_review`, `add_pr_comment` *(NEW in v3.0.0)* |
+| **Pull Requests** | `list_pull_requests`, `get_pull_request`, `get_pr_diff`, `get_pr_comments`, `create_pr_review`, `add_pr_comment` |
 | Validation | `validate_repo_org`, `get_branch_protection` |

 ### NetBox MCP Server (shared)
@@ -186,7 +211,7 @@ Comprehensive NetBox REST API integration for infrastructure management.
 | Virtualization | Clusters, VMs, Interfaces |
 | Extras | Tags, Custom Fields, Audit Log |

-### Data Platform MCP Server (shared) *NEW in v4.0.0*
+### Data Platform MCP Server (shared)

 pandas, PostgreSQL/PostGIS, and dbt integration for data engineering.

@@ -197,7 +222,7 @@ pandas, PostgreSQL/PostGIS, and dbt integration for data engineering.
 | PostGIS | `st_tables`, `st_geometry_type`, `st_srid`, `st_extent` |
 | dbt | `dbt_parse`, `dbt_run`, `dbt_test`, `dbt_build`, `dbt_compile`, `dbt_ls`, `dbt_docs_generate`, `dbt_lineage` |

-### Viz Platform MCP Server (shared) *NEW in v4.0.0*
+### Viz Platform MCP Server (shared)

 Dash Mantine Components validation and visualization tools.

@@ -209,7 +234,7 @@ Dash Mantine Components validation and visualization tools.
 | Theme | `theme_create`, `theme_extend`, `theme_validate`, `theme_export_css`, `theme_list`, `theme_activate` |
 | Page | `page_create`, `page_add_navbar`, `page_set_auth`, `page_list`, `page_get_app_config` |

-### Contract Validator MCP Server (shared) *NEW in v5.0.0*
+### Contract Validator MCP Server (shared)

 Cross-plugin compatibility validation tools.

--- a/docs/CANONICAL-PATHS.md
+++ b/docs/CANONICAL-PATHS.md
@@ -2,7 +2,7 @@

 **This file defines ALL valid paths in this repository. No exceptions. No inference. No assumptions.**

-Last Updated: 2026-01-30 (v5.4.1)
+Last Updated: 2026-02-04 (v7.1.0)

 ---

@@ -12,10 +12,18 @@ Last Updated: 2026-01-30 (v5.4.1)
 leo-claude-mktplace/
 ├── .claude/                    # Claude Code local settings
 ├── .claude-plugin/             # Marketplace manifest
-│   └── marketplace.json
+│   ├── marketplace.json
+│   ├── marketplace-lean.json   # Lean profile (6 core plugins)
+│   └── marketplace-full.json   # Full profile (all plugins)
+├── .mcp-lean.json              # Lean profile MCP config (gitea only)
+├── .mcp-full.json              # Full profile MCP config (all servers)
 ├── .scratch/                   # Transient work (auto-cleaned)
 ├── docs/                       # All documentation
 │   ├── architecture/           # Draw.io diagrams and specs
+│   ├── prompts/                # Shared prompt templates
+│   │   └── INDEX.md            # Prompt template index
+│   ├── project-lessons-learned/ # Project-level lessons (not sprint-specific)
+│   │   └── INDEX.md            # Lessons index
 │   ├── CANONICAL-PATHS.md      # This file - single source of truth
 │   ├── COMMANDS-CHEATSHEET.md  # All commands quick reference
 │   ├── CONFIGURATION.md        # Centralized configuration guide
@@ -150,7 +158,9 @@ leo-claude-mktplace/
 │   ├── validate-marketplace.sh # Marketplace compliance validation
 │   ├── verify-hooks.sh         # Verify all hooks use correct event types
 │   ├── setup-venvs.sh          # Setup MCP server venvs (create only, never delete)
-│   └── release.sh              # Release automation with version bumping
+│   ├── release.sh              # Release automation with version bumping
+│   ├── claude-launch.sh        # Task-specific launcher with profile selection
+│   └── switch-profile.sh       # DEPRECATED: use claude-launch.sh instead
 ├── CLAUDE.md
 ├── README.md
 ├── LICENSE
@@ -168,6 +178,7 @@ leo-claude-mktplace/
 |---------|---------|---------|
 | Plugin location | `plugins/{plugin-name}/` | `plugins/projman/` |
 | Plugin manifest | `plugins/{plugin-name}/.claude-plugin/plugin.json` | `plugins/projman/.claude-plugin/plugin.json` |
+| Plugin MCP mapping (optional) | `plugins/{plugin-name}/.claude-plugin/metadata.json` | `plugins/projman/.claude-plugin/metadata.json` |
 | Plugin commands | `plugins/{plugin-name}/commands/` | `plugins/projman/commands/` |
 | Plugin agents | `plugins/{plugin-name}/agents/` | `plugins/projman/agents/` |
 | Plugin skills | `plugins/{plugin-name}/skills/` | `plugins/projman/skills/` |
@@ -305,6 +316,7 @@ All MCP servers are defined in `.mcp.json` at repository root:

 | Date | Change | By |
 |------|--------|-----|
+| 2026-02-04 | v7.1.0: Added profile configs, prompts/, project-lessons-learned/, metadata.json, deprecated switch-profile.sh | Claude Code |
 | 2026-01-30 | v5.5.0: Removed plugin-level mcp-servers symlinks - all MCP config now in root .mcp.json | Claude Code |
 | 2026-01-26 | v5.0.0: Added contract-validator plugin and MCP server | Claude Code |
 | 2026-01-26 | v4.1.0: Added viz-platform plugin and MCP server | Claude Code |
--- a/docs/DEBUGGING-CHECKLIST.md
+++ b/docs/DEBUGGING-CHECKLIST.md
@@ -279,8 +279,8 @@ Error: Could not find a suitable TLS CA certificate bundle, invalid path:

 Use these commands for automated checking:

- `/debug report` - Run full diagnostics, create issue if problems found
- `/debug review` - Investigate existing diagnostic issues and propose fixes
+- `/pm-debug report` - Run full diagnostics, create issue if problems found
+- `/pm-debug review` - Investigate existing diagnostic issues and propose fixes

 ---

--- a/docs/prompts/INDEX.md
+++ b/docs/prompts/INDEX.md
--- a/plugins/cmdb-assistant/.claude-plugin/metadata.json
+++ b/plugins/cmdb-assistant/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["netbox"]}
--- a/plugins/contract-validator/.claude-plugin/metadata.json
+++ b/plugins/contract-validator/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["contract-validator"]}
--- a/plugins/data-platform/.claude-plugin/metadata.json
+++ b/plugins/data-platform/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["data-platform"]}
--- a/plugins/data-platform/skills/visual-header.md
+++ b/plugins/data-platform/skills/visual-header.md
@@ -14,16 +14,18 @@ Display at the start of every command execution:

 | Command | Header Text |
 |---------|-------------|
-| initial-setup | Setup Wizard |
-| ingest | Ingest |
-| profile | Data Profile |
-| schema | Schema Explorer |
+| data-setup | Setup Wizard |
+| data-ingest | Ingest |
+| data-profile | Data Profile |
+| data-schema | Schema Explorer |
 | data-quality | Data Quality |
-| run | dbt Run |
+| data-run | dbt Run |
 | dbt-test | dbt Tests |
-| lineage | Lineage |
+| data-lineage | Lineage |
 | lineage-viz | Lineage Visualization |
-| explain | Model Explanation |
+| data-explain | Model Explanation |
+| data-review | Data Review |
+| data-gate | Data Gate |

 ## Summary Box Format

--- a/plugins/doc-guardian/.claude-plugin/metadata.json
+++ b/plugins/doc-guardian/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["gitea"]}
--- a/plugins/git-flow/.claude-plugin/metadata.json
+++ b/plugins/git-flow/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["gitea"]}
--- a/plugins/git-flow/commands/git-status.md
+++ b/plugins/git-flow/commands/git-status.md
@@ -51,6 +51,6 @@ Unstaged:
 2. Ready to commit with 1 staged file

 --- Quick Actions ---
-/commit - Commit staged changes
-/commit-push - Commit and push
+/git-commit - Commit staged changes
+/git-commit-push - Commit and push
 ```
--- a/plugins/git-flow/skills/visual-header.md
+++ b/plugins/git-flow/skills/visual-header.md
@@ -19,28 +19,28 @@ Standard header format for consistent visual output across all git-flow commands

 ## Command Headers

-### /commit
+### /git-commit
 ```
 +----------------------------------------------------------------------+
 |  GIT-FLOW Smart Commit                                               |
 +----------------------------------------------------------------------+
 ```

-### /commit-push
+### /git-commit-push
 ```
 +----------------------------------------------------------------------+
 |  GIT-FLOW Commit & Push                                              |
 +----------------------------------------------------------------------+
 ```

-### /commit-sync
+### /git-commit-sync
 ```
 +----------------------------------------------------------------------+
 |  GIT-FLOW Commit Sync                                                |
 +----------------------------------------------------------------------+
 ```

-### /commit-merge
+### /git-commit-merge
 ```
 +----------------------------------------------------------------------+
 |  GIT-FLOW Commit & Merge                                             |
--- a/plugins/pr-review/.claude-plugin/metadata.json
+++ b/plugins/pr-review/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["gitea"]}
--- a/plugins/projman/.claude-plugin/metadata.json
+++ b/plugins/projman/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["gitea"]}
--- a/plugins/projman/CONFIGURATION.md
+++ b/plugins/projman/CONFIGURATION.md
@@ -5,6 +5,6 @@ See **[docs/CONFIGURATION.md](../../docs/CONFIGURATION.md)** for complete setup
 ## Quick Commands

 ```
-/initial-setup    # First time on this machine
-/project-init     # New project (system already configured)
+/pm-setup --full   # First time on this machine
+/pm-setup --quick  # New project (system already configured)
 ```
--- a/plugins/projman/commands/sprint-close.md
+++ b/plugins/projman/commands/sprint-close.md
@@ -14,6 +14,7 @@ agent: orchestrator
 - skills/progress-tracking.md
 - skills/git-workflow.md
 - skills/sprint-lifecycle.md
+- skills/token-budget-report.md

 ## Purpose

@@ -82,3 +83,12 @@ If the sprint was linked to an RFC:
 ║  [Sprint Name]                                                   ║
 ╚══════════════════════════════════════════════════════════════════╝
 ```
+
+## Final Step: Token Budget Report
+
+After displaying the closing summary and completing all workflow steps, generate a Token Budget Report per `skills/token-budget-report.md`.
+
+- Phase: CLOSING
+- List all skills that were loaded during this closing session
+- Use the orchestrator agent's model (sonnet) for agent overhead
+- Display the formatted report
--- a/plugins/projman/commands/sprint-plan.md
+++ b/plugins/projman/commands/sprint-plan.md
@@ -20,6 +20,7 @@ agent: planner
 - skills/planning-workflow.md
 - skills/label-taxonomy/labels-reference.md
 - skills/sprint-lifecycle.md
+- skills/token-budget-report.md

 ## Purpose

@@ -57,3 +58,12 @@ Execute the planning workflow as defined in `skills/planning-workflow.md`.
 ║  [Sprint Name]                                                   ║
 ╚══════════════════════════════════════════════════════════════════╝
 ```
+
+## Final Step: Token Budget Report
+
+After displaying the planning summary and gaining sprint approval, generate a Token Budget Report per `skills/token-budget-report.md`.
+
+- Phase: PLANNING
+- List all skills that were loaded during this planning session
+- Use the planner agent's model (sonnet) for agent overhead
+- Display the formatted report
--- a/plugins/projman/commands/sprint-status.md
+++ b/plugins/projman/commands/sprint-status.md
@@ -1,46 +1,80 @@
 ---
-description: Check current sprint progress, identify blockers, optionally generate dependency diagram
+description: Check current sprint progress, identify blockers, optionally generate dependency diagram or token budget report
 ---

 # Sprint Status

 ## Skills Required

+**Always loaded:**
 - skills/mcp-tools-reference.md
- skills/progress-tracking.md
- skills/dependency-management.md
- skills/sprint-lifecycle.md
+
+**Conditional — only load if matching flag is present:**
+- skills/sprint-lifecycle.md — load if displaying lifecycle state (always, but this is small)
+- skills/dependency-management.md — load ONLY with `--diagram` flag
+- skills/token-budget-report.md — load ONLY with `--tokens` flag
+- skills/progress-tracking.md — load ONLY with `--diagram` flag

 ## Purpose

-Check current sprint progress, identify blockers, and show execution status. Optionally generate a visual dependency diagram.
+Check current sprint progress, identify blockers, and show execution status. Optionally generate a visual dependency diagram or token budget report.

 ## Invocation

 ```
 /sprint-status              # Text-based status report
 /sprint-status --diagram    # Include Mermaid dependency diagram
+/sprint-status --tokens     # Show token budget estimation report
 ```

 ## Workflow

-0. **Display Lifecycle State** - Read current Sprint/* state from milestone description per `skills/sprint-lifecycle.md` and display in output header.
-1. **Fetch Sprint Issues** - Get all issues for current milestone
-2. **Calculate Progress** - Count completed vs total issues
-3. **Identify Active Tasks** - Find issues with `Status/In-Progress`
-4. **Identify Blockers** - Find issues with `Status/Blocked`
-5. **Show Dependency Status** - Which tasks are now unblocked
-6. **Parse Progress Comments** - Extract real-time status from structured comments
+1. **Fetch Active Milestone** — `get_milestone` for the open milestone
+2. **Read Lifecycle State** — Parse `**Sprint State:**` from milestone description
+3. **Fetch Sprint Issues** — `list_issues` filtered by milestone
+4. **Calculate Progress** — Count closed vs total issues
+5. **Identify Blockers** — Find issues with `Status/Blocked` label
+6. **Display Output** — Format header + progress bar + issue table + blockers

-### If --diagram flag:
+That's it. No dependency analysis, no token estimation, no progress comment parsing unless a flag asks for it.

-7. **Fetch Dependencies** - Use `list_issue_dependencies` for each issue
-8. **Get Execution Order** - Use `get_execution_order` for batch grouping
-9. **Generate Mermaid Syntax** - Create flowchart with status colors
+### If --diagram flag, THEN ALSO:
+7. Fetch dependencies with `list_issue_dependencies`
+8. Load `skills/dependency-management.md`
+9. Load `skills/progress-tracking.md`
+10. Generate Mermaid diagram
+
+### If --tokens flag, THEN ALSO:
+11. Load `skills/token-budget-report.md`
+12. **Generate Token Budget Report** - Execute `skills/token-budget-report.md` estimation model
+    - Phase: STATUS (read-only snapshot, not a workflow boundary)
+    - List MCP servers from `.mcp.json` with static overhead estimates
+    - Show current session cost estimate based on skills loaded so far
+    - Display formatted report per the skill's Display Format section

 ## Output Format

-See `skills/progress-tracking.md` for the progress display format.
+### Default Output (no flags)
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  📋 PROJMAN                                                      ║
+║  📊 STATUS                                                       ║
+║  [Sprint Name]                                                   ║
+╚══════════════════════════════════════════════════════════════════╝
+
+Sprint State: [Planning|Executing|Blocked|Review|Closing]
+
+Progress: [██████████░░░░░░░░░░] 50% (5/10 issues)
+
+| # | Title | Status | Labels |
+|---|-------|--------|--------|
+| 123 | Issue title | Open | Priority/High |
+| 124 | Another issue | Closed | Type/Bug |
+
+Blockers:
+- #125: Blocked issue title (Status/Blocked)
+```

 ### Diagram Format (--diagram)

@@ -68,13 +102,3 @@ flowchart TD
 | In Progress | Yellow | #FFD700 |
 | Open | Blue | #ADD8E6 |
 | Blocked | Red | #FFB6C1 |
-
-## Visual Output
-
-```
-╔══════════════════════════════════════════════════════════════════╗
-║  📋 PROJMAN                                                      ║
-║  📊 STATUS                                                       ║
-║  [Sprint Name]                                                   ║
-╚══════════════════════════════════════════════════════════════════╝
-```
--- a/plugins/projman/skills/token-budget-report.md
+++ b/plugins/projman/skills/token-budget-report.md
@@ -0,0 +1,115 @@
+---
+description: Token consumption estimation model and display format for sprint workflows
+---
+
+# Token Budget Report
+
+## Purpose
+
+Provides directional token consumption estimates at sprint workflow boundaries. Not exact — Claude Code doesn't expose token metrics — but accurate enough to identify which phases and components consume the most context budget.
+
+## When to Display
+
+- End of `/sprint-plan` (after all issues created)
+- End of `/sprint-close` (after lessons captured)
+- On explicit request: `/sprint-status --tokens`
+
+---
+
+## Estimation Model
+
+### MCP Tool Definitions (Static Overhead)
+
+These are loaded once at session start. Update this table if MCP servers change.
+
+| MCP Server | Default Tools | Est. Tokens | With Module Filter |
+|------------|--------------|-------------|-------------------|
+| netbox | 182 | ~19,810 | ~4,500 (dcim,ipam,virt,extras) |
+| gitea | 36 | ~4,785 | — |
+| data-platform | 32 | ~3,458 | — |
+| viz-platform | 20 | ~3,055 | — |
+| contract-validator | 8 | ~1,048 | — |
+| **Total (default)** | **278** | **~32,156** | — |
+| **Total (filtered)** | **~139** | **~16,846** | — |
+
+### Skill Loading (Per Phase)
+
+| Phase | Typical Skills Loaded | Est. Tokens |
+|-------|----------------------|-------------|
+| Planning (`/sprint-plan`) | mcp-tools-reference, label-taxonomy, sprint-planning, architecture-analysis, rfc-workflow | ~3,000–5,000 |
+| Execution (`/sprint-start`) | mcp-tools-reference, branch-security, plan-then-batch | ~2,000–3,000 |
+| Review (`/pm-review`) | mcp-tools-reference, review-checklist | ~1,500–2,500 |
+| Close (`/sprint-close`) | mcp-tools-reference, sprint-lifecycle, lessons-learned | ~2,000–3,000 |
+
+To get actual numbers: count characters in each skill file loaded during the phase, divide by 4.
+
+### Agent Overhead
+
+| Agent | Model | Est. Overhead per Invocation |
+|-------|-------|------------------------------|
+| Planner | sonnet | ~500 tokens (frontmatter + system context) |
+| Orchestrator | sonnet | ~500 tokens |
+| Executor | sonnet | ~400 tokens |
+| Code Reviewer | sonnet | ~400 tokens |
+
+---
+
+## Display Format
+
+```
+-- Token Budget Report -----------------------------------------------+
+|  Phase: [PLANNING / CLOSING]                                         |
+|  Sprint: [Sprint Name]                                               |
+----------------------------------------------------------------------+
+|                                                                      |
+|  MCP Overhead (session-wide):                                        |
+|    netbox ........... ~4,500 tk  (filtered: dcim,ipam,virt,extras)   |
+|    gitea ............ ~4,785 tk                                      |
+|    data-platform .... ~3,458 tk                                      |
+|    viz-platform ..... ~3,055 tk                                      |
+|    contract-valid ... ~1,048 tk                                      |
+|    Subtotal ......... ~16,846 tk                                     |
+|                                                                      |
+|  This Phase:                                                         |
+|    Skills loaded .... ~X,XXX tk  (N files)                           |
+|    Agent overhead ... ~X,XXX tk  (model: sonnet)                     |
+|    Command file ..... ~XXX tk                                        |
+|    Subtotal ......... ~X,XXX tk                                      |
+|                                                                      |
+|  Estimated Session Total: ~XX,XXX tk                                 |
+|  Typical Claude Code Budget: ~200,000 tk                             |
+|  Estimated Usage: ~XX%                                               |
+|                                                                      |
+|  Tip: Run `/doctor` for exact MCP overhead numbers.                  |
+----------------------------------------------------------------------+
+```
+
+---
+
+## Instructions for the Agent
+
+When generating this report:
+
+1. **MCP Overhead**: List the MCP servers from `.mcp.json` and use the static token estimates from the table above. If `NETBOX_ENABLED_MODULES` is set in the environment, use the filtered estimate for netbox.
+
+2. **Skills Loaded**: Count the skill files that were loaded (referenced in the command's "Skills Required" section). Estimate tokens by reading each file's character count and dividing by 4.
+
+3. **Agent Overhead**: Use the table above based on which agent ran during this phase.
+
+4. **Totals**: Sum the phase subtotal. Add to MCP overhead for session estimate.
+
+5. **Percentage**: Express as a percentage of ~200,000 tokens (typical Claude Code context window).
+
+---
+
+## Accuracy Disclaimer
+
+These are estimates based on known file sizes and static overhead tables. Actual consumption varies based on:
+- Conversation length
+- Tool call results (especially large grep/read outputs)
+- File content read during the session
+- Number of agent invocations
+
+For exact MCP overhead, run `/doctor`.
+
+This report helps identify which *components* consume the most budget — not the precise total.
--- a/plugins/projman/skills/visual-output.md
+++ b/plugins/projman/skills/visual-output.md
@@ -99,3 +99,22 @@ For domain gate results displayed by orchestrator:
 | Hourglass | In progress |
 | Empty box | Pending / Not started |
 | Warning | Warning |
+
+---
+
+## Token Budget Report
+
+Displayed at end of planning and closing phases:
+
+```
+-- Token Budget Report -----------------------------------------------+
+|  Phase: [PHASE NAME]                                                 |
+|  Sprint: [Sprint Name]                                               |
+----------------------------------------------------------------------+
+|  MCP Overhead: ~XX,XXX tk                                            |
+|  Phase Cost:   ~X,XXX tk  (skills: N, agent: model)                 |
+|  Est. Total:   ~XX,XXX tk (~XX% of budget)                          |
+----------------------------------------------------------------------+
+```
+
+See `skills/token-budget-report.md` for full format and estimation model.
--- a/plugins/viz-platform/.claude-plugin/metadata.json
+++ b/plugins/viz-platform/.claude-plugin/metadata.json
@@ -0,0 +1 @@
+{"mcp_servers": ["viz-platform"]}
--- a/plugins/viz-platform/claude-md-integration.md
+++ b/plugins/viz-platform/claude-md-integration.md
@@ -44,9 +44,9 @@ If using with data-platform, add this section:
 ## Data + Visualization Workflow

 ### Data Loading (data-platform)
- `/ingest {file}` - Load CSV, Parquet, or JSON
- `/schema {table}` - View database schema
- `/profile {data_ref}` - Statistical summary
+- `/data-ingest {file}` - Load CSV, Parquet, or JSON
+- `/data-schema {table}` - View database schema
+- `/data-profile {data_ref}` - Statistical summary

 ### Visualization (viz-platform)
 - `/viz-chart {type}` - Create charts from loaded data
--- a/scripts/claude-launch.sh
+++ b/scripts/claude-launch.sh
@@ -0,0 +1,91 @@
+#!/usr/bin/env bash
+#
+# claude-launch.sh - Launch Claude Code with task-specific plugin profiles
+#
+# Usage: ./scripts/claude-launch.sh [profile] [extra-args...]
+#
+# Profiles:
+#   sprint  - Project management, git, PR review, security, docs (default)
+#   infra   - Infrastructure/CMDB management
+#   data    - Data engineering and visualization
+#   review  - Code review only (lightweight)
+#   full    - All plugins via marketplace.json (~22K tokens)
+#
+# Examples:
+#   ./scripts/claude-launch.sh                    # Default sprint profile
+#   ./scripts/claude-launch.sh sprint             # Explicit sprint profile
+#   ./scripts/claude-launch.sh data --model opus  # Data profile with Opus
+#   ./scripts/claude-launch.sh full               # Load all plugins
+#
+
+set -euo pipefail
+
+# Colors for output
+CYAN='\033[0;36m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+# Script directory (for relative plugin paths)
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(dirname "$SCRIPT_DIR")"
+PLUGINS_DIR="$REPO_ROOT/plugins"
+
+# Default profile
+PROFILE="${1:-sprint}"
+
+# Shift profile arg if provided (to pass remaining args to claude)
+if [[ $# -gt 0 ]]; then
+    shift
+fi
+
+# Define plugin lists for each profile
+declare -A PROFILES
+PROFILES[sprint]="projman git-flow pr-review code-sentinel doc-guardian clarity-assist"
+PROFILES[infra]="cmdb-assistant"
+PROFILES[data]="data-platform viz-platform"
+PROFILES[review]="pr-review code-sentinel"
+PROFILES[full]=""  # Empty = use marketplace.json
+
+# Validate profile
+if [[ ! ${PROFILES[$PROFILE]+_} ]]; then
+    echo -e "${YELLOW}Unknown profile: $PROFILE${NC}"
+    echo "Available profiles: sprint, infra, data, review, full"
+    exit 1
+fi
+
+# Build --plugin-dir arguments
+PLUGIN_ARGS=()
+PLUGIN_LIST="${PROFILES[$PROFILE]}"
+
+if [[ -n "$PLUGIN_LIST" ]]; then
+    echo -e "${CYAN}Profile: $PROFILE${NC}"
+    echo -e "${GREEN}Loading plugins:${NC}"
+
+    for plugin in $PLUGIN_LIST; do
+        plugin_path="$PLUGINS_DIR/$plugin"
+        if [[ -d "$plugin_path" ]]; then
+            echo "  • $plugin"
+            PLUGIN_ARGS+=("--plugin-dir" "$plugin_path")
+        else
+            echo -e "${YELLOW}  ⚠ $plugin (not found at $plugin_path)${NC}"
+        fi
+    done
+    echo ""
+else
+    echo -e "${CYAN}Profile: full${NC}"
+    echo -e "${GREEN}Loading all plugins via marketplace.json${NC}"
+    echo ""
+fi
+
+# Enable MCP Tool Search for deferred tool loading
+export ENABLE_TOOL_SEARCH=true
+echo -e "${GREEN}MCP Tool Search: enabled${NC}"
+echo ""
+
+# Launch claude with plugin args and any extra arguments
+if [[ ${#PLUGIN_ARGS[@]} -gt 0 ]]; then
+    exec claude "${PLUGIN_ARGS[@]}" "$@"
+else
+    exec claude "$@"
+fi
--- a/scripts/install-plugin.sh
+++ b/scripts/install-plugin.sh
@@ -116,19 +116,19 @@ validate_target() {
 }

 # --- Get MCP Servers for Plugin ---
-# Reads the mcp_servers array from plugin.json
+# Reads the mcp_servers array from metadata.json (separate from plugin.json to avoid schema validation issues)
 # Returns newline-separated list of MCP server names, or empty if none
 get_mcp_servers() {
    local plugin_name="$1"
-    local plugin_json="$REPO_ROOT/plugins/$plugin_name/.claude-plugin/plugin.json"
+    local metadata_json="$REPO_ROOT/plugins/$plugin_name/.claude-plugin/metadata.json"

-    if [[ ! -f "$plugin_json" ]]; then
+    if [[ ! -f "$metadata_json" ]]; then
        return
    fi

-    # Read mcp_servers array from plugin.json
+    # Read mcp_servers array from metadata.json
    # Returns empty if field doesn't exist or is empty
-    jq -r '.mcp_servers // [] | .[]' "$plugin_json" 2>/dev/null || true
+    jq -r '.mcp_servers // [] | .[]' "$metadata_json" 2>/dev/null || true
 }

 # --- Check if plugin has any MCP servers ---
--- a/scripts/list-installed.sh
+++ b/scripts/list-installed.sh
@@ -68,16 +68,16 @@ get_available_plugins() {
 }

 # --- Get MCP Servers for Plugin ---
-# Reads the mcp_servers array from plugin.json
+# Reads the mcp_servers array from metadata.json (separate from plugin.json to avoid schema validation issues)
 get_mcp_servers() {
    local plugin_name="$1"
-    local plugin_json="$REPO_ROOT/plugins/$plugin_name/.claude-plugin/plugin.json"
+    local metadata_json="$REPO_ROOT/plugins/$plugin_name/.claude-plugin/metadata.json"

-    if [[ ! -f "$plugin_json" ]]; then
+    if [[ ! -f "$metadata_json" ]]; then
        return
    fi

-    jq -r '.mcp_servers // [] | .[]' "$plugin_json" 2>/dev/null || true
+    jq -r '.mcp_servers // [] | .[]' "$metadata_json" 2>/dev/null || true
 }

 # --- Check if plugin has any MCP servers defined ---
--- a/scripts/switch-profile.sh
+++ b/scripts/switch-profile.sh
@@ -0,0 +1,61 @@
+#!/usr/bin/env bash
+# Switch between marketplace profiles
+# Usage: ./scripts/switch-profile.sh [lean|full]
+
+set -euo pipefail
+
+echo "⚠️  DEPRECATED: use scripts/claude-launch.sh instead." >&2
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ROOT_DIR="$(dirname "$SCRIPT_DIR")"
+MARKETPLACE_DIR="$ROOT_DIR/.claude-plugin"
+
+case "${1:-lean}" in
+  lean)
+    cp "$MARKETPLACE_DIR/marketplace-lean.json" "$MARKETPLACE_DIR/marketplace.json"
+    cp "$ROOT_DIR/.mcp-lean.json" "$ROOT_DIR/.mcp.json"
+    rm -rf ~/.claude/plugins/cache/
+    echo "Switched to LEAN profile (6 plugins, 1 MCP server)"
+    echo "Plugin cache cleared."
+    echo ""
+    echo "Plugins: projman, git-flow, pr-review, clarity-assist, code-sentinel, doc-guardian"
+    echo "MCP: gitea only"
+    echo ""
+    echo "Restart Claude Code session for changes to take effect."
+    ;;
+  full)
+    cp "$MARKETPLACE_DIR/marketplace-full.json" "$MARKETPLACE_DIR/marketplace.json"
+    cp "$ROOT_DIR/.mcp-full.json" "$ROOT_DIR/.mcp.json"
+    rm -rf ~/.claude/plugins/cache/
+    echo "Switched to FULL profile (12 plugins, 5 MCP servers)"
+    echo "Plugin cache cleared."
+    echo ""
+    echo "Plugins: all"
+    echo "MCP: gitea, netbox, data-platform, viz-platform, contract-validator"
+    echo ""
+    echo "Restart Claude Code session for changes to take effect."
+    ;;
+  status)
+    # Check current profile by comparing files
+    if diff -q "$MARKETPLACE_DIR/marketplace.json" "$MARKETPLACE_DIR/marketplace-lean.json" >/dev/null 2>&1; then
+      echo "Current profile: LEAN (6 plugins, 1 MCP server)"
+    elif diff -q "$MARKETPLACE_DIR/marketplace.json" "$MARKETPLACE_DIR/marketplace-full.json" >/dev/null 2>&1; then
+      echo "Current profile: FULL (12 plugins, 5 MCP servers)"
+    else
+      echo "Current profile: CUSTOM (marketplace.json differs from both profiles)"
+    fi
+    ;;
+  *)
+    echo "Usage: $0 [lean|full|status]"
+    echo ""
+    echo "Profiles:"
+    echo "  lean    — 6 core plugins (projman, git-flow, pr-review, clarity-assist, code-sentinel, doc-guardian)"
+    echo "            1 MCP server (gitea only)"
+    echo "  full    — All 12 plugins"
+    echo "            5 MCP servers (gitea, netbox, data-platform, viz-platform, contract-validator)"
+    echo "  status  — Show current profile"
+    echo ""
+    echo "Note: Restart Claude Code session after switching for changes to take effect."
+    exit 1
+    ;;
+esac
--- a/scripts/uninstall-plugin.sh
+++ b/scripts/uninstall-plugin.sh
@@ -77,19 +77,19 @@ validate_target() {
 }

 # --- Get MCP Servers for Plugin ---
-# Reads the mcp_servers array from plugin.json
+# Reads the mcp_servers array from metadata.json (separate from plugin.json to avoid schema validation issues)
 # Returns newline-separated list of MCP server names, or empty if none
 get_mcp_servers() {
    local plugin_name="$1"
-    local plugin_json="$REPO_ROOT/plugins/$plugin_name/.claude-plugin/plugin.json"
+    local metadata_json="$REPO_ROOT/plugins/$plugin_name/.claude-plugin/metadata.json"

-    if [[ ! -f "$plugin_json" ]]; then
+    if [[ ! -f "$metadata_json" ]]; then
        return
    fi

-    # Read mcp_servers array from plugin.json
+    # Read mcp_servers array from metadata.json
    # Returns empty if field doesn't exist or is empty
-    jq -r '.mcp_servers // [] | .[]' "$plugin_json" 2>/dev/null || true
+    jq -r '.mcp_servers // [] | .[]' "$metadata_json" 2>/dev/null || true
 }

 # --- Remove from .mcp.json ---
--- a/scripts/validate-marketplace.sh
+++ b/scripts/validate-marketplace.sh
@@ -206,6 +206,35 @@ for plugin_dir in "$PLUGINS_DIR"/*/; do
    echo "✓ $plugin_name valid"
 done

+echo ""
+echo "=== Validating Plugin Metadata (MCP Mappings) ==="
+
+for plugin_dir in "$PLUGINS_DIR"/*/; do
+    plugin_name=$(basename "$plugin_dir")
+    metadata_json="$plugin_dir.claude-plugin/metadata.json"
+
+    if jq -e '.mcp_servers' "$plugin_dir.claude-plugin/plugin.json" >/dev/null 2>&1; then
+        echo "ERROR: $plugin_name/plugin.json contains 'mcp_servers' — move to metadata.json"
+        exit 1
+    fi
+
+    if [[ -f "$metadata_json" ]]; then
+        if ! jq empty "$metadata_json" 2>/dev/null; then
+            echo "ERROR: Invalid JSON in $plugin_name/.claude-plugin/metadata.json"
+            exit 1
+        fi
+        mcp_servers=$(jq -r '.mcp_servers // [] | .[]' "$metadata_json" 2>/dev/null)
+        for server in $mcp_servers; do
+            if [[ ! -d "$ROOT_DIR/mcp-servers/$server" ]]; then
+                echo "ERROR: $plugin_name metadata.json references '$server' but mcp-servers/$server/ missing"
+                exit 1
+            fi
+            echo "  ✓ $plugin_name → $server"
+        done
+    fi
+done
+echo "✓ Plugin metadata validation passed"
+
 # CRITICAL: Validate marketplace.json file references
 echo ""
 echo "=== Validating Marketplace File References (CRITICAL) ==="
Author	SHA1	Message	Date
Leo Miranda	d13c310e67	Merge pull request 'development' (#442 ) from development into main Reviewed-on: #442	2026-02-05 02:39:33 +00:00
Leo Miranda	faafbd56f5	Merge pull request 'fix: audit fixes — metadata.json, stale profiles, canonical paths, validation' (#441 ) from fix/audit-metadata-profiles-validation into development Reviewed-on: #441	2026-02-05 02:39:17 +00:00
lmiranda	7380b07312	fix: audit fixes — metadata.json, stale profiles, canonical paths, validation - Confirmed/created projman metadata.json with gitea mapping - Synced profile JSONs to current version - Added metadata.json validation to validate-marketplace.sh - Updated CANONICAL-PATHS.md to current version - Deprecated switch-profile.sh in favor of claude-launch.sh Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 21:36:49 -05:00
Leo Miranda	4cbcc7d391	Merge pull request 'development' (#440 ) from development into main Reviewed-on: #440	2026-02-04 23:13:00 +00:00
Leo Miranda	4baad6c2b5	Merge pull request 'docs: remove stale NEW markers and fix changelog accuracy' (#439 ) from docs/cleanup-stale-markers into development Reviewed-on: #439	2026-02-04 23:12:46 +00:00
lmiranda	398fc50099	docs: remove stale NEW markers and fix changelog accuracy - Remove 10 stale "NEW in vX.X.X" markers from README.md - Fix CHANGELOG [7.1.0] to clarify switch-profile.sh is superseded - Correct that full profile is the default baseline (not lean) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 18:11:43 -05:00
Leo Miranda	7b127d8e5c	Merge pull request 'development' (#438 ) from development into main Reviewed-on: #438	2026-02-04 23:07:11 +00:00
Leo Miranda	ba7350e130	Merge pull request 'chore: release v7.1.0' (#437 ) from chore/release-v7.1.0 into development Reviewed-on: #437	2026-02-04 23:06:54 +00:00
lmiranda	4b7c40e1f5	chore: release v7.1.0 - Task-specific launcher script (claude-launch.sh) with profiles - Lean/full profile switching for token optimization - Token usage estimation via /sprint-status --tokens - Conditional skill loading in /sprint-status - Fixed stale command references in docs Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 18:05:18 -05:00
Leo Miranda	9673c0c994	Merge pull request 'development' (#436 ) from development into main Reviewed-on: #436	2026-02-04 22:54:47 +00:00
Leo Miranda	e1d1ffc555	Merge pull request 'fix: restore full profile as baseline for claude-launch.sh' (#435 ) from fix/restore-full-profile into development Reviewed-on: #435	2026-02-04 22:54:30 +00:00
lmiranda	318d027bfa	fix: restore full profile as baseline for claude-launch.sh claude-launch.sh uses --plugin-dir for selective loading, making lean/full profile switching obsolete. Full marketplace.json is now the permanent baseline. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 17:52:13 -05:00
Leo Miranda	34a5e4a5a3	Merge pull request 'development' (#434 ) from development into main Reviewed-on: #434	2026-02-04 21:52:56 +00:00
Leo Miranda	9710d296e4	Merge pull request 'feat: add task-specific launcher script with MCP Tool Search' (#433 ) from feat/task-specific-launcher into development Reviewed-on: #433	2026-02-04 21:52:40 +00:00
lmiranda	59b5545a9b	feat: add task-specific launcher script with MCP Tool Search New script scripts/claude-launch.sh provides profile-based plugin loading using --plugin-dir to reduce token overhead from ~22K to ~4-6K tokens. Profiles: sprint, infra, data, review, full. Enables MCP Tool Search for deferred tool loading. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 16:51:42 -05:00
Leo Miranda	b3c388b732	Merge pull request 'development' (#432 ) from development into main Reviewed-on: #432	2026-02-04 20:40:28 +00:00
Leo Miranda	a4fb5b6feb	Merge pull request 'fix: move mcp_servers to metadata.json to prevent silent plugin.json rejection' (#431 ) from fix/mcp-servers-metadata-json into development Reviewed-on: #431	2026-02-04 20:40:06 +00:00
lmiranda	de4126bf68	fix: move mcp_servers to metadata.json to prevent silent plugin.json rejection Claude Code's strict schema validation silently rejects plugins with unknown root-level fields in plugin.json (anthropics/claude-code#20409). Moved mcp_servers to separate metadata.json files. Updated install/uninstall/list scripts to read from new location. Added cache clearing to switch-profile.sh. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 13:46:43 -05:00
Leo Miranda	5a8c3b041f	Merge pull request 'development' (#430 ) from development into main Reviewed-on: #430	2026-02-04 17:23:24 +00:00
Leo Miranda	33a7c91f4f	Merge pull request 'feat: Token consumption overhaul - lean/full profile switching' (#429 ) from feat/token-consumption-overhaul into development Reviewed-on: #429	2026-02-04 17:23:07 +00:00
lmiranda	8781179fd0	feat(marketplace): add lean/full profile switching for token optimization - Add marketplace-lean.json (6 plugins) and marketplace-full.json (12 plugins) - Add .mcp-lean.json (gitea only) and .mcp-full.json (5 servers) - Create scripts/switch-profile.sh for easy profile switching - Update sprint-status.md with conditional skill loading - Set lean profile as default (~14k token savings) Lean profile includes: projman, git-flow, pr-review, clarity-assist, code-sentinel, doc-guardian Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 12:22:36 -05:00
Leo Miranda	7d0b6050f9	Merge pull request 'development' (#428 ) from development into main Reviewed-on: #428	2026-02-04 16:01:15 +00:00
Leo Miranda	6209ab9597	Merge pull request 'feat(projman): wire --tokens flag into /sprint-status' (#427 ) from feat/sprint-status-tokens-flag into development Reviewed-on: #427	2026-02-04 16:00:58 +00:00
lmiranda	2c41ca338d	feat(projman): wire --tokens flag into /sprint-status Add token budget reporting option to sprint-status command: - Update description to mention token budget report - Add token-budget-report.md to skills list - Add --tokens invocation option - Add workflow section for generating token report Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 10:59:38 -05:00
Leo Miranda	34fc1d842c	Merge pull request 'development' (#426 ) from development into main Reviewed-on: #426	2026-02-04 15:25:55 +00:00
Leo Miranda	9eece4daa3	Merge pull request 'fix: v7.0.1 stale reference cleanup + token usage reporting' (#425 ) from fix/v7-stale-refs-and-token-reporting into development Reviewed-on: #425	2026-02-04 15:25:37 +00:00
lmiranda	871d1bff58	chore: add v7.0.1 changelog entries - Fixed: stale command references documentation updates - Added: token usage estimation reporting feature Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 10:22:15 -05:00
lmiranda	d90a8d05af	feat(projman): add token usage estimation reporting - New skill: token-budget-report.md with MCP overhead and skill loading estimation model based on known file sizes and static overhead tables - Sprint-plan displays token report after planning complete - Sprint-close displays token report after lessons captured - Visual-output.md updated with token report format - .gitignore exception for token-budget-report.md (not API tokens) Helps identify which phases and components consume the most context budget. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 10:20:56 -05:00
lmiranda	044c49ba95	fix(docs): update stale command references post v7.0.0 namespace rename - data-platform/skills/visual-header.md: updated command mapping table - viz-platform/claude-md-integration.md: fixed cross-plugin section - git-flow/commands/git-status.md: updated quick actions - git-flow/skills/visual-header.md: updated command header sections - projman/CONFIGURATION.md: updated quick commands to pm-setup - docs/DEBUGGING-CHECKLIST.md: fixed /debug to /pm-debug All command references now use v7.0.0 namespaced names. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-02-04 10:18:19 -05:00
Leo Miranda	ab3847c656	Merge pull request 'development' (#424 ) from development into main Reviewed-on: #424	2026-02-04 02:53:11 +00:00
Leo Miranda	76105e98e0	Merge pull request 'refactor!: Command namespace rename (v7.0.0 breaking change)' (#423 ) from refactor/command-namespace-rename into development Reviewed-on: #423	2026-02-04 02:52:53 +00:00
Leo Miranda	49891c1e0c	Merge pull request 'development' (#422 ) from development into main Reviewed-on: #422	2026-02-04 01:09:37 +00:00
Leo Miranda	c6182a3fda	Merge pull request 'feat(projman): add plan-then-batch skill optimization' (#421 ) from feat/plan-then-batch-optimization into development Reviewed-on: #421	2026-02-04 00:59:03 +00:00