commit-synclisted

# commit-sync Goal: never let code and the knowledge layer drift apart, and never push junk or secrets. One procedure: sync → message → confirm → commit → push. ## Step 1 — Review what changed ```bash git status --porcelain git diff --stat git diff # actually read it ``` Identify which services/contracts/agents/skills the change touches. ## Step 2 — Sync the knowledge layer (the "update skills and agents" part) > The `pre-commit` staleness gate (`.claude/hooks/pre-commit`) enforces the > *structural* floor automatically — it will **block** the commit if a contract/ > schema/service or an agent/skill changed without its map/README staged. This step > is how you satisfy that gate, plus the semantic part it can't check (findings/ > decisions). Don't rely on `--no-verify` to skip it. Apply the **context-management** skill (knowledge-keeper discipline). For this diff: - Contract/routing-key/table/object-store-key changed → update the shared-models index `CLAUDE.md` + the service `CLAUDE.md` + `.claude/context/SERVICE-MAP.md` + `.claude/context/DATA-FLOW.md` (nodes/authority/rules if the data shape or ownership moved). - A bug fixed / root cause confirmed → update its `F-###` in `.claude/context/FINDINGS.md` (status OPEN→FIXED, add the fixing commit). - A design decision made → add a `D-###` to `.claude/context/DECISIONS.md`. - **An agent or skill added/removed/renamed** → update `.claude/agents/README.md` (routing table) so it stays the source of truth. - A `CLAUDE.m