ai-commitlisted

# Commit Workflow Governed commit pipeline: stage, format, lint, secret-detect, compose message, push. Honors CLAUDE.md Don't rules (binding). Use `/ai-pr` when the goal is a pull request. ``` /ai-commit # auto-stage, format, lint, scan, commit, push /ai-commit --only path/to/file.py # stage only the named files /ai-commit "fix(auth): ..." # provide a message hint ``` ## Process ### 0. Auto-branch from protected If current branch is `main`/`master`: infer type (`feat/`, `fix/`, `chore/`, `docs/`, `refactor/`), generate slug deterministically with `python3 .ai-engineering/scripts/branch_slug.py --prefix <type>` (reads spec.md frontmatter), then `git checkout -b <output>`, report new branch. ### 1. Work item context (optional) If `.ai-engineering/specs/spec.md` frontmatter has `refs`: include work item refs as commit body trailers (`Refs: AB#101, AB#102, #45`). Only include `close_on_pr` items — never features. ### 2. Instinct consolidation If `.ai-engineering/observations/observations.yml` exists, run `/ai-session-watch --review` to consolidate session observations before committing. ### 3. Stage changes `git add <file1> <file2>` selectively. Use `git add -A` only when explicitly requested. Exclude generated files, secrets, large binaries. ### 4. Run gate orchestrator ``` ai-eng gate run --cache-aware --json --mode=local ``` The orchestrator runs the 2-wave collector (Wave 1 fixers serial -> Wave 2 checkers parallel) with cache-