メニュー
Run the repo health gate before commit or push to reduce doc drift and keep branches clean. Triggers on commit, push, before push, repo health, reduce drift, doc drift, clean branch.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | repo-health |
| description | Run the repo health gate before commit or push to reduce doc drift and keep branches clean. Triggers on commit, push, before push, repo health, reduce drift, doc drift, clean branch. |
| user-invocable | true |
Run the health gate before committing or pushing so the tree stays clean and entropy (doc drift, broken refs, invalid task defs) is caught early.
docs/, configs/, or benchmarks/ task dirs.Quick (docs + selection file only; use after editing only docs/config):
cd ~/CodeScaleBench && python3 scripts/repo_health.py --quick
Full (adds task preflight static; use before merge or after touching task defs):
cd ~/CodeScaleBench && python3 scripts/repo_health.py
docs/REPO_HEALTH.md for common fixes).Do not suggest committing or pushing with failing health checks. If the user insists, remind them that CI will fail and main stays clean only if everyone runs the gate.
The list of checks is in configs/repo_health.json. Quick mode runs only quick_checks; full runs all required checks.
docs/REPO_HEALTH.md — Full doc (what’s checked, branch hygiene, fixing failures).scripts/repo_health.py — Gate script; exit 0 only when all required checks pass.Archive old completed benchmark runs to save disk space and speed up scans. Triggers on archive runs, clean up runs, disk space, old runs.
Audit benchmark suites against ABC framework (Task/Outcome/Reporting validity). Checks instruction quality, verifier correctness, reproducibility. Triggers on benchmark audit, audit benchmark, abc audit, task validity.
Verify infrastructure readiness before launching benchmark runs — tokens, Docker, disk, credentials. Triggers on check infra, infrastructure check, ready to run, pre-run check.
Compare benchmark results across agent configurations (baseline, SG_full). Show where configs diverge. Triggers on compare configs, config comparison, which config wins, MCP impact.
Token and cost analysis per run, suite, and config. Shows most expensive tasks and config cost comparison. Triggers on cost report, how much did it cost, token usage, spending.
Generate the aggregate CSB evaluation report from completed Harbor runs. Triggers on generate report, eval report, ccb report, benchmark report.