Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/kewton/commandmate/uat-fix-loopgit clone --depth 1 https://github.com/Kewton/CommandMateWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.02897 |
| Opus 5 | $0.00016 | $0.01448 |
| Sonnet 5 | $0.00006 | $0.00579 |
| Haiku 4.5 | $0.00003 | $0.00290 |
Grade A, and why
uat-fix-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UAT修正ループ
概要
受入テスト(UAT)で不合格となったIssueについて、featureブランチでの修正→再PR→再マージ→再UATのサイクルを自動化します。全テストがPASSするか、最大リトライ回数に達するまでループを繰り返します。
使用方法
/uat-fix-loop [Issue番号1] [Issue番号2] .../uat-fix-loop [Issue番号] --max-retry 5(最大リトライ回数を指定)
前提条件
- developブランチ上で実行すること
- 直前に
/uatが実行済みで、FAILしたテスト項目があること - FAILしたIssueのfeatureブランチ worktreeが存在すること
- CommandMateサーバーが稼働していること
実行内容
あなたはQAマネージャーとして、UAT不合格項目の修正サイクルを統括します。
パラメータ
- issue_numbers: 修正対象のIssue番号(スペース区切り)
- --max-retry: 最大リトライ回数(デフォルト: 3)
Step 0: 初期設定
TodoWriteツールで作業計画を作成:
- [ ] Step 1: UAT結果の分析
- [ ] Step 2: 修正指示の送信
- [ ] Step 3: 修正完了待ち・品質確認
- [ ] Step 4: 再PR・再マージ
- [ ] Step 5: 再UAT
- [ ] Step 6: 結果判定(→ ループ or 完了)
Step 1: UAT結果の分析
1-1. 直前のUATレポートを読み込む
各Issueについて、最新のUATレポートからFAIL項目を抽出:
for issue_num in {issue_numbers}; do
# UATレポートを確認
ls dev-reports/issue/${issue_num}/uat/
cat dev-reports/issue/${issue_num}/uat/test-results.json 2>/dev/null
done
1-2. FAIL項目の整理
各FAIL項目について以下を記録:
- テストID: テスト項目の識別子
- テスト項目名: 何をテストしたか
- 期待結果: 何が期待されていたか
- 実際の結果: 何が起きたか
- エビデンス: テスト出力の関連部分
1-3. 修正対象のworktree特定
for issue_num in {issue_numbers}; do
WT_ID=$(commandmatedev ls --branch "feature/${issue_num}" --quiet)
echo "Issue #${issue_num} → Worktree: ${WT_ID}"
done
worktreeが見つからない場合はエラー報告して中断。
Step 2: 修正指示の送信
各FAILしたIssueのワーカーに修正指示を送信。
2-1. 修正指示メッセージの構築
FAIL項目の情報を具体的に含めた修正指示を構築する:
受入テスト(UAT)で以下のテスト項目がFAILしました。修正してください。
## FAIL項目
### {テストID}: {テスト項目名}
- 期待結果: {期待されていた動作}
- 実際の結果: {実際に起きた動作}
- エビデンス: {テスト出力の関連部分}
- 推定原因: {ログから推定される原因}
## 修正後の確認事項
修正が完了したら、以下を順に実行してください:
1. npm run lint
2. npx tsc --noEmit
3. npm run test:unit
4. 修正内容をコミット
5. git push
2-2. 送信
for each fail_issue:
commandmatedev send <worktree-id> "{修正指示メッセージ}" \
--auto-yes --duration 2h
修正指示が並列送信可能な場合(独立したIssueのFAIL)は並列で送信する。
Step 3: 修正完了待ち・品質確認
3-1. 完了待機
for each worktree:
commandmatedev wait <worktree-id> --timeout 7200
EXIT=$?
if [ "$EXIT" -eq 10 ]; then
# プロンプト検出 → 内容確認して応答
commandmatedev respond <worktree-id> "yes"
commandmatedev wait <worktree-id> --timeout 7200
fi
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 339 lines · 32 tokens per session scan A 30d4dc23c88b
uat-fix-loop is a command published in the GitHub repository Kewton/CommandMate (39 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 2,897 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
crow-image
Show an image in Crow's Images panel — pass the file path as the argument.
release-notes
Draft release notes, recommend and apply a version bump, and update CHANGELOG.md for the next dormouse release by analyzing all merge commits and squash-merged PRs since the last release tag. Used as step 2 of the release checklist in docs/specs/deploy.md.
e2e
使用 Playwright 对 Web UI 进行端到端测试(支持视频录制、Trace 录制、控制台/网络日志捕获).
debug-playwright
Use this command to debug failing Playwright tests in a source-first, evidence-first workflow.
run-all-tests-and-fix
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality. All test-related commands must pass before completion.
test
Agentic end-to-end test orchestrator — drive web/macOS flows, evaluate UX rubric, reconcile issues.