Menü
Rebuild the cqs index and show before/after stats comparison.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Run a multi-category code audit on the cqs codebase. Spawns parallel agents per batch.
Trust-boundary security audit of cqs — fans out unbiddable-auditor agents across 6 categories (RT-INJ/RT-FS/RT-RES/RT-DATA/RT-RELAY/RT-EXFIL), attacker mindset, run-the-attack PoC + regression guard.
Run the retrieval recall gate with dead-gold triage and the binary A/B regression test. Required before release tags; use after any retrieval-adjacent merge.
Run after making changes, before committing — reviews the current git diff for impact and risk via cqs review.
Release a new version of cqs. Bumps version, updates changelog, runs the recall gate, publishes to crates.io, creates GitHub release.
One-command setup for cqs in a new project — skills, tears infrastructure, CLAUDE.md, init, index.
| name | reindex |
| description | Rebuild the cqs index and show before/after stats comparison. |
| disable-model-invocation | false |
| argument-hint | [--force] |
Rebuild the cqs search index and compare stats.
Before stats: Run cqs stats and capture output (chunk count, note count, HNSW status)
Reindex:
cqs index (incremental — only re-embeds changed files)--force argument: cqs index --force (full rebuild). Stop the daemon first (systemctl --user stop cqs-watch) — cqs itself warns to do this — and restart it after.After stats: Run cqs stats again
Compare: Show before/after diff:
Verify: Run a quick search to confirm index is working:
cqs "parse source file" — should return resultsdocs/notes.toml manually (if cqs watch isn't running)