Separate cognitive work from mechanical API execution to reduce
skill-related token consumption by ~76-83% during sprint workflows.
Changes:
- Add batch-execution.md skill with 4-phase protocol
- Promote mcp-tools-reference and batch-execution to frontmatter
for planner and orchestrator agents (auto-injected, zero re-read)
- Replace "Skills to Load" with phase-based "Skill Loading Protocol"
- Restructure planning-workflow.md Steps 8-10 for batch execution
- Update agent matrix in CLAUDE.md and docs/CONFIGURATION.md
- Add Phase-Based Skill Loading documentation section
- Clean up .gitignore (transient files, dev symlinks)
Token impact:
- 6-issue sprint planning: ~76% reduction
- 10-issue sprint planning: ~80% reduction
- 8-issue status updates: ~83% reduction
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New skill: sprint-lifecycle.md defines states, transitions, and check protocol
- All sprint commands now check and set lifecycle state
- States tracked in milestone description metadata (Sprint/Planning, Sprint/Executing, Sprint/Reviewing)
- Out-of-order calls produce warnings with guidance
- --force override available for all lifecycle checks
- Added Sprint/* labels to label taxonomy documentation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- sprint-approval.md: approval is now a hard block, not a warning
- sprint-start.md: added --force flag documentation
- orchestrator.md: approval verification is now a hard stop
- docs: updated commands cheatsheet
BREAKING: /sprint-start now requires approval or --force flag
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
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>
