benjaminshoemaker/ai_coding_project_base - Page 2

populate-state

Generate `.claude/phase-state.json` from the main execution plan and git history. Use to recover phase state after context loss or when joining an existing project.

verify-task

Run code-verification on a specific task. Use to verify a single task's acceptance criteria after implementation.

capture-learning

Capture a project learning or pattern to LEARNINGS.md. Use when you discover a useful pattern or convention during development.

run-todos

Implement [ready]-tagged TODO items with commits. Use after /list-todos has clarified requirements and marked items as ready.

criteria-audit

Validate EXECUTION_PLAN.md for verification metadata, manual reasons, and testability. Use when preparing Phase 1 or after editing EXECUTION_PLAN.md.

data-flow-audit

Detect split data source anti-patterns and scattered business rule duplication where the same logic is reimplemented across multiple files and languages. Catches semantic duplication that syntactic tools like jscpd miss. Use at phase checkpoints or when…

review-deferred

Review deferred verification items. Use when you want to check or clear the deferred review queue without waiting for project completion.

update-docs

Update documentation after commits. Syncs README, AGENTS.md, CHANGELOG, and docs/ with code changes. Use after commits or to analyze working tree changes.

vision-audit

Audit project alignment with VISION.md, identify SDLC gaps, and generate feature proposals. Use when reviewing strategic direction or planning new features.

audit-agentsmd

Audit AGENTS.md (or CLAUDE.md) for length, attention-zone misplacement, and extraction opportunities. Produces a prioritized report with reordering and extraction recommendations. Use when AGENTS.md exceeds 400 lines, after major additions, or when agent…

list-todos

Analyze and prioritize TODO items from TODOS.md. Use when planning work or deciding what to implement next.