Sprint-plan approval workflow:
- Request explicit approval after creating issues
- Present scope summary (branches, files, dependencies)
- User must type "approve sprint N" to authorize
- Record approval in milestone description with timestamp
Sprint-start verification:
- Check milestone for "## Sprint Approval" section
- If missing, STOP and direct to /sprint-plan
- Extract approved scope (branches, files)
- Enforce scope during execution
Orchestrator scope enforcement:
- Verify approval before any execution
- Check each operation against approved scope
- Operations outside scope require re-approval
This separates planning (review) from execution (action),
preventing agents from executing without explicit user consent.
Closes#233
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Executor checkpointing:
- Standard checkpoint comment format with branch, commit, phase
- Files modified with status (created, modified)
- Completed and pending steps tracking
- State notes for resumption context
- Save checkpoint after major steps, before stopping
Orchestrator resume detection:
- Scan issue comments for "## Checkpoint" markers
- Offer resume options: resume, start fresh, review details
- Verify branch exists and files match before resuming
- Dispatch executor with checkpoint context
Sprint-start integration:
- Checkpoint detection as first workflow step
- Resume flow documentation with example
- Checkpoint format specification
This enables resuming work after:
- Budget exhaustion (100 tool call limit)
- Agent failure/circuit breaker
- Manual interruption
- Session timeout
Closes#237
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add pre-dispatch conflict detection:
- Analyze target files for each task before parallel dispatch
- Check for file overlap between tasks in same batch
- If overlap detected, sequentialize those specific tasks
- Example analysis showing conflict detection workflow
Branch isolation protocol:
- Each task MUST have its own branch
- Never have two agents work on the same branch
- Sequential merge after completion (not simultaneous)
- Handle merge conflicts by stopping second task
Conflict resolution rules:
- Same file → MUST sequentialize
- Same directory → Usually safe, review
- Shared config → Sequentialize
- Shared test fixture → Sequentialize or assign different files
This prevents parallel agents from modifying the same files
and causing git merge conflicts.
Closes#234
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add structured progress comment format for agents:
- Standard format with Status, Phase, Tool Calls budget
- Completed/In-Progress/Blockers/Next sections
- Clear examples for starting, blocked, and failed states
- Guidance on when to post (every 20-30 tool calls)
Update sprint-status.md:
- Document how to parse progress comments
- Show enhanced in-progress display with tool call tracking
- Add progress comment detection to blocker analysis
This enables users to see:
- Real-time agent progress
- Tool call budget consumption
- Current phase and step
- Blockers as they occur
Closes#232
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Status/In-Progress, Status/Blocked, Status/Failed, Status/Deferred labels
- Update orchestrator.md with Status Label Management section
- Update executor.md with honest Status Reporting requirements
- Update labels-reference.md with Status detection guidelines
Status labels enable accurate tracking:
- In-Progress: Work actively being done
- Blocked: Waiting for dependency/external factor
- Failed: Attempted but couldn't complete
- Deferred: Moved to future sprint
Agents must report honestly - never say "completed" when blocked/failed.
Closes#235
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The Claude plugin cache at ~/.claude/plugins/cache/leo-claude-mktplace/
holds versioned copies of .mcp.json files. When we update .mcp.json
to use run.sh instead of direct python paths, the cache retains old
versions, causing MCP servers to fail.
Now post-update.sh clears this cache, forcing Claude to read fresh
configs from the installed marketplace on next session start.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace direct python path in .mcp.json with run.sh wrapper scripts
that automatically locate the venv in cache or local directory.
Problem: .venv symlinks are gitignored, causing them to be wiped on
every git operation. The SessionStart hook should recreate them but
this was unreliable, leading to repeated MCP server failures.
Solution: run.sh scripts that:
- First check ~/.cache/claude-mcp-venvs/leo-claude-mktplace/{server}/.venv
- Fallback to local .venv if exists
- Exit with helpful error if neither found
This eliminates dependency on symlinks entirely - the scripts are
tracked in git and will always be present after clone/pull/update.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem:
- Venvs in marketplace directory got deleted on every update
- Users had to manually run setup.sh and wait for full pip install
- This caused MCP servers to fail until manually fixed
Solution:
- Store venvs in external cache (~/.cache/claude-mcp-venvs/)
- Auto-repair symlinks via SessionStart hook (instant operation)
- Only run pip install on first use or when requirements change
Architecture:
Cache (runtime) → Marketplaces → External venv cache
The chain of symlinks ensures all three locations work:
1. ~/.claude/plugins/cache/.../mcp-servers/* (runtime)
2. ~/.claude/plugins/marketplaces/.../mcp-servers/* (install)
3. ~/.cache/claude-mcp-venvs/* (persistent venvs)
Performance:
- First install: ~2-3 min (unchanged)
- After marketplace update: 0.03 sec (was 2-3 min)
Files:
- scripts/venv-repair.sh: Fast symlink restoration for hooks
- scripts/setup-venvs.sh: Full setup with external cache
- plugins/projman/hooks/startup-check.sh: Auto-repair on session start
- .gitignore: Ignore .venv symlinks
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem: Version workflow was documented but not enforced in sprint-close.
After completing sprints, CHANGELOG wasn't updated and releases weren't created.
Solution:
- Add "Update CHANGELOG" as mandatory step 7 in sprint-close
- Add "Version Check" as step 8 with /suggest-version and release.sh
- Update orchestrator agent with CHANGELOG and version reminders
- Add V04.1.0 wiki workflow changes to CHANGELOG [Unreleased]
- Document MCP bug #160 in Known Issues
This ensures versioning workflow is part of the sprint close process,
not just documented in CLAUDE.md.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create new proposal-status.md command
- Shows all proposals with status (Pending, In Progress, Implemented, Abandoned)
- Tree view of implementations under each proposal
- Links to issues and lessons learned
- Update README with new command documentation
Phase 4 of V04.1.0 Wiki-Based Planning Enhancement.
Closes#164
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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>
ALL hooks now use command type (bash scripts) instead of prompt type.
Prompt hooks are unreliable - model ignores instructions.
Changes:
- projman: SessionStart → startup-check.sh with [projman] prefix
- pr-review: SessionStart → startup-check.sh with [pr-review] prefix
- project-hygiene: cleanup.sh now has [project-hygiene] prefix
- doc-guardian: already fixed (notify.sh with [doc-guardian] prefix)
- code-sentinel: already fixed (security-check.sh with [code-sentinel] prefix)
All hook output now guaranteed to have plugin name prefix.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add protected branch detection to /commit command (Step 1)
- Warn users before committing to protected branches
- Offer to create feature branch automatically
- Rewrite doc-guardian hook to be truly non-blocking
- Enforce strict [plugin-name] prefix in all hook outputs
- Add forbidden words list to prevent accidental blocking
Fixes#109, #110
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add [plugin-name] prefix to all hook messages for better identification
- Make doc-guardian hook notification-only (non-blocking)
- Add stale branch detection to /commit-sync with git fetch --prune
- Enhance /branch-cleanup to handle stale branches separately
Closes improvements for hook UX and git workflow
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>
Remove incorrect nested matcher/hooks structure from SessionStart hooks.
SessionStart events don't use matchers - that format is only for tool-based
hooks like PreToolUse/PostToolUse.
Fixes recurring "SessionStart:startup hook error" on Claude Code startup.
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>
Claude Code v2.0.44 doesn't support the agents field in plugin manifests.
Removed from: clarity-assist, pr-review, projman, claude-config-maintainer, cmdb-assistant
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update all references from old names to new marketplace identity:
- support-claude-mktplace → leo-claude-mktplace (URLs)
- lm-claude-plugins → leo-claude-mktplace (repo name)
- Claude Code Marketplace → Leo Claude Marketplace (display name)
Files updated:
- Core docs (CLAUDE.md, README.md, CHANGELOG.md)
- Documentation (CANONICAL-PATHS, CONFIGURATION, UPDATING, COMMANDS-CHEATSHEET)
- Marketplace manifest and all 9 plugin.json files
- Plugin READMEs and MCP server READMEs
- Setup script and label taxonomy reference
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>
Version standardization:
- Move version to main README.md title: "Claude Code Marketplace - v2.2.0"
- Remove version from plugins/projman/README.md title
- Remove version from plugins/projman/CONFIGURATION.md title
- Remove version from plugin listings in README.md
- Remove "Key Features (v2.2.0)" -> "Key Features"
- Remove Version section from plugins/projman/README.md
- Remove version references from CLAUDE.md structure comments
Added versioning rule to CLAUDE.md:
- Version displayed ONLY in main README.md title
- Do NOT add versions to plugin docs or config guides
- Version history maintained in CHANGELOG.md only
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Version updates:
- marketplace.json metadata.version: 2.0.0 → 2.2.0
- marketplace.json projman version: 2.0.0 → 2.2.0
- plugins/projman/plugin.json version: 2.0.0 → 2.2.0
Documentation updates:
- CHANGELOG.md: Changed [Unreleased] to [2.2.0] - 2026-01-20
- README.md: Updated projman version to v2.2.0
- README.md: Added /review and /test-check to commands list
- README.md: Added code-reviewer to agent list
- README.md: Updated Key Features section to v2.2.0
- README.md: Added validate-marketplace.sh to structure
- plugins/projman/README.md: Updated title to v2.2.0
- plugins/projman/README.md: Updated version changelog
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
