← ClaudeAtlas

context-checklisted

Optional manual drift audit — report stale provenance-tracked docs (via _provenancelib drift detection across .codearbiter/.provenance/), then per stale doc offer re-scout / re-baseline / defer. Not the daily loop; commit-gate auto-heal owns routine maintenance.
arbiterForge/codeArbiter · ★ 141 · AI & Automation · score 78
Install: claude install-skill arbiterForge/codeArbiter
# context-check An optional, on-demand drift audit for bypass cases: a merge or an external edit drifted a tracked source file you are not about to commit, so commit-gate's Phase 5.5 auto-heal did not fire. This skill reports stale docs and lets you act on each one individually. This skill is NOT in the daily loop. Commit-gate auto-heal (Phase 5.5, `heal_worklist`) owns the routine maintenance path. Invoke this only when drift was introduced outside a commit (e.g. a direct push, a merge you did not author, a manual file edit). ## Pre-flight Read these before computing drift: 1. `.codearbiter/.provenance/` — the per-doc provenance records. Load all records via `load_provenance_dir` from [hooks/_provenancelib.py](../../hooks/_provenancelib.py). 2. `.codearbiter/code-map.md` — coarse concern map; read to orient on which modules the stale docs govern. ## Flow ### Step 1 — Compute drift Use `_provenancelib` helpers in this order: 1. `load_provenance_dir(root + "/.codearbiter/.provenance/")` — returns the provenance map `{doc: record}`. 2. Collect all `drift_trigger: true` paths across all records. 3. `batch_hash(paths, runner)` — hash every existing path in one git call. 4. `compute_drift(provenance_map, current_hashes)` — returns a drift report `{doc: [{path, kind}]}` for docs that have stale sources. Alternatively reuse the same logic as `startup_drift_line` by calling it for a human-readable summary, then inspecting `compute_drift` directly for detail.