- Add Metadata section to lesson structure with Implementation link
- Update lesson examples to include metadata with wiki reference
- Enable bidirectional traceability: lessons ↔ implementation pages
Phase 3 of V04.1.0 Wiki-Based Planning Enhancement.
Closes#163
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add step 5: Update wiki implementation page status (Implemented/Partial/Failed)
- Add step 6: Update wiki proposal page when all implementations complete
- Add update_wiki_page to MCP tools in both sprint-close.md and orchestrator.md
- Add critical reminders for wiki status updates
Implements Phase 2 of V04.1.0 Wiki-Based Planning Enhancement.
Closes#162
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 1 implementation for Change V04.1.0:
- Add flexible input source detection (file, wiki, conversation)
- Add wiki proposal and implementation page creation
- Add wiki reference to created issues
- Add cleanup step to delete local files after migration
- Update planner agent with wiki workflow responsibilities
Closes#161
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- doc-guardian: Hook now tracks documentation dependencies and outputs
specific files needing updates (e.g., commands → COMMANDS-CHEATSHEET.md)
- projman: SessionStart hook now suggests /sprint-plan when open issues
exist without milestone, and warns about unreleased CHANGELOG entries
- projman: Add /suggest-version command for semantic version recommendations
- docs: Update COMMANDS-CHEATSHEET.md with data-platform plugin (was missing)
- docs: Update CLAUDE.md with data-platform and version 4.0.0
Fixes documentation drift and lack of proactive workflow suggestions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a new "user-reported" mode alongside the existing automated
diagnostics mode. Users can now choose to:
1. Run automated diagnostics (existing behavior)
2. Report an issue they experienced while using any plugin command
User-reported mode:
- Step 0: Mode selection via AskUserQuestion
- Step 0.1: Structured feedback gathering
- Which plugin/command was affected
- What the user was trying to do
- What went wrong (error, missing feature, unexpected behavior, docs)
- Expected vs actual behavior
- Any workarounds found
- Step 5.1: Smart label generation based on problem type
- Step 6.1: User-friendly issue template with investigation hints
This allows capturing UX issues, missing features, and documentation
problems that wouldn't be caught by automated MCP tool tests.
Fixes#139
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes multiple issues from diagnostic #123:
1. create_label_smart type safety (labels.py)
- Add isinstance(result, dict) checks after API calls
- Return structured error dict if API returns unexpected type
- Prevents "list indices must be integers" crash
2. debug-report always uses curl with labels
- Remove MCP option - always use curl for marketplace issues
- Add label ID fetching step (Source/Diagnostic, Type/Bug)
- Include labels in curl POST payload
- Avoids branch protection restrictions on main branch
Fixes#123
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The MCP server's branch-aware security blocks write operations on
protected branches (main, fix/*, etc). After pushing a feature branch
and creating a PR, we must switch back to development before adding
comments to issues via MCP tools.
When MCP tools are not available in a session (the very scenario
/debug-report is designed to diagnose), the command now falls back to:
1. Check for Gitea credentials at ~/.config/claude/gitea.env
2. Use curl + jq to create the issue via Gitea REST API
3. If no credentials, save report to local file for manual submission
Security measures:
- Uses mktemp -m 600 for restrictive file permissions
- Uses jq --rawfile for safe JSON construction (no command substitution)
- Proper cleanup of temporary files
Fixes#100
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New commands for structured debugging workflow:
/debug-report (for test projects):
- Runs 5 diagnostic MCP tool tests
- Captures full project context (git remote, cwd, branch)
- Generates structured issue with hypothesis
- Creates issue in marketplace repo automatically
/debug-review (for marketplace repo):
- Lists open diagnostic issues for triage
- Maps errors to relevant code files
- MANDATORY: Reads files before proposing fixes
- Three human approval gates
- Creates feature branch, commits, PR with linking
Also includes:
- Dynamic label format detection in suggest_labels
- Rewritten labels-sync.md with explicit execution steps
- Version bump to 3.1.0
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
ROOT CAUSE: The MCP server runs with cwd set to the plugin directory,
not the user's project. It cannot auto-detect the repository.
SOLUTION: The command documentation now explicitly instructs Claude to:
1. Run `git remote get-url origin` via Bash first
2. Parse the URL to extract owner/repo
3. Pass repo parameter to ALL MCP tool calls
Also removed the "Label Reference" section that was causing Claude
to ask about creating a local reference file.
Key changes:
- Added "CRITICAL: Execution Steps" section with numbered steps
- Added "DO NOT" section to prevent common mistakes
- Removed confusing reference file documentation
- Made all MCP tool calls show required repo parameter
Fixes#77
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The command description still said "updates the local reference file"
which caused the agent to prompt about creating a reference file.
Updated to clarify: no local files are created or modified.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates labels-sync.md to:
- Remove [Y/n] prompts that suggested manual confirmation
- Clarify that execution is autonomous
- Document that labels are fetched dynamically (not from reference file)
- Update examples to show actual behavior
- Improve troubleshooting for common issues
- Add user-owned repo handling documentation
Related to #67
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add /project-init and /project-sync commands to projman
- Add setup commands (/initial-setup, /project-init, /project-sync) to pr-review
- Add /initial-setup to cmdb-assistant
- Replace manual MCP setup instructions with /initial-setup wizard
- Move GITEA_ORG from system-level to project-level in examples
- Add COMMANDS-CHEATSHEET.md and UPDATING.md to documentation table
- Fix GITEA_ORG validation in projman initial-setup (was checking system config)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Major improvements to plugin setup experience:
Setup Commands:
- Redesign /initial-setup as interactive wizard (MCP + system + project config)
- Add /project-init for quick project-only setup
- Add /project-sync for handling repository moves/renames
- Add Gitea API validation to auto-fill org/repo when verified
Configuration Changes:
- Move GITEA_ORG from system to project level (supports multi-org users)
- System config now only contains GITEA_URL and GITEA_TOKEN
- Project .env now contains GITEA_ORG and GITEA_REPO
Automation:
- Add SessionStart hook for projman and pr-review
- Automatically detects git remote vs .env mismatch
- Warns user to run /project-sync when mismatch found
Documentation:
- Unify configuration docs (remove duplicate in plugins/projman)
- Add flow diagrams to CONFIGURATION.md
- Add setup script review guidance to UPDATING.md
- Update COMMANDS-CHEATSHEET.md with new commands and hooks
Files added:
- plugins/projman/commands/project-init.md
- plugins/projman/commands/project-sync.md
- plugins/projman/hooks/hooks.json
- plugins/pr-review/commands/initial-setup.md
- plugins/pr-review/commands/project-init.md
- plugins/pr-review/commands/project-sync.md
- plugins/pr-review/hooks/hooks.json
- plugins/cmdb-assistant/commands/initial-setup.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds test generation command that complements existing /test-check:
- Auto-detects test framework (pytest, jest, vitest, go test, etc.)
- Generates unit, integration, e2e, or snapshot tests
- Creates happy path, edge case, and error tests
- Supports multiple languages (Python, JavaScript, Go, etc.)
- Integrates with /test-check for generate-then-verify workflow
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add test-check.md command for pre-sprint-close test verification
- Automatic framework detection (pytest, jest, go test, cargo, etc.)
- Coverage reporting when available
- Sprint file analysis for untested changes
- Clear pass/fail summary with recommendations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Major fixes for Claude Code plugin installation:
1. Moved marketplace.json to repo root (.claude-plugin/)
- Fixes known bug #11243, #11278 with local marketplace path resolution
- Claude Code uses marketplace.json file path as base, not directory
2. Simplified plugin.json manifests
- Removed commands/agents/skills directory declarations
- Claude Code auto-discovers these from standard directories
- Specifying directories caused "must end with .md" validation errors
3. Cleaned command frontmatter
- Removed non-standard fields (name, agent, arguments)
- Only description field is valid in command frontmatter
4. Removed deprecated claude-plugin-developer skill
- Skill was never properly integrated
- Removed from repo and all documentation references
All three plugins now validate successfully:
- projman: Sprint planning with Gitea/Wiki.js
- cmdb-assistant: NetBox CMDB integration
- project-hygiene: Post-task cleanup hooks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Created plugins/ directory to centralize all plugins
- Moved projman and project-hygiene into plugins/
- Updated .mcp.json paths from ../mcp-servers/ to ../../mcp-servers/
- Updated CLAUDE.md governance section with new directory structure
- Updated README.md with new repository structure diagram
- Fixed all path references in documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
