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 skills add kyto64/codex-pr-review-toolkit-minimal --skill comment-analyzergit clone --depth 1 https://github.com/kyto64/codex-pr-review-toolkit-minimalWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kyto64/codex-pr-review-toolkit-minimal/comment-analyzer)<a href="https://agentmods.dev/skills/kyto64/codex-pr-review-toolkit-minimal/comment-analyzer"><img src="https://agentmods.dev/badge/skills/kyto64/codex-pr-review-toolkit-minimal/comment-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kyto64/codex-pr-review-toolkit-minimal/comment-analyzer"><img src="https://agentmods.dev/badge/skills/kyto64/codex-pr-review-toolkit-minimal/comment-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00037 | $0.01327 |
| Opus 5 | $0.00018 | $0.00664 |
| Sonnet 5 | $0.00007 | $0.00265 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
comment-analyzer 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment Analyzer
PR で追加・変更されたコードコメントおよびリポジトリ docs(README、LICENSE、NOTICE、attribution、SECURITY、CONTRIBUTING 等)の事実の正確性と長期保守性をレビューする。数ヶ月後にコンテキストなしでコードや docs を読む保守者の視点で、コメント rot や docs の陳腐化による技術的負債を防ぐ。pr-review の comments 観点として使う。
レビュー観点
1. コードコメントの事実の正確性(実装と突き合わせて検証する)
- パラメータ・戻り値の記述がシグネチャと一致しているか
- 記述された振る舞いが実際のロジックと一致しているか
- 参照している型・関数・変数が実在するか
- 言及されたエッジケースが実際にコードで処理されているか
- 計算量・パフォーマンスの主張が正確か
2. リポジトリ docs の事実の正確性(リポジトリ実態と突き合わせて検証する)
- README のコマンド例・手順が実際の CLI やスクリプトと一致するか
- パス、ファイル名、generated/source-of-truth の説明がリポジトリ実態と一致するか
- license、NOTICE、upstream path、third-party attribution の主張が一次ソースと一致するか
- security / support / contribution policy がリポジトリの実態と矛盾しないか
3. 完全性
- 非自明な前提・事前条件が書かれているか
- 副作用、重要なエラー条件が説明されているか
- 複雑なアルゴリズムのアプローチ、自明でないビジネス上の理由が説明されているか
4. 長期価値
- 「なぜ」を説明しているか。自明な「何」の繰り返しは削除候補
- 近い将来のコード変更で陳腐化しやすい記述(一時的状態への言及など)がないか
5. 誤解の余地
- 複数に解釈できる曖昧な表現
- リファクタ済みコードへの古い参照、現実装と一致しない例
- すでに解決済みの TODO / FIXME
外部出典・ライセンス・attribution の確認
外部 repo、license、NOTICE、upstream path、third-party notice を主張する変更では、可能なら一次ソースで確認する。
- upstream の agent path が attribution table と一致するか
- upstream に NOTICE があるか/ないかの主張が実態と一致するか
- local LICENSE が upstream plugin LICENSE と byte-for-byte で一致するか(主張がある場合)
確認できない場合: 不確実な推測を Finding にしない。Notes に「未検証: [項目]」として残す。legal / attribution correctness を推測で断定しない。
重要度の目安
| 状況 | 重要度 |
|---|---|
| 誤ったコメントや docs が誤った修正・運用を誘発する | P1 |
| 重要な前提が欠けている、陳腐化しやすい記述 | P2 |
| 削除推奨の無価値コメント | P3(pr-review では通常除外) |
出力
Finding がある場合、または Finding はないが未検証の外部出典など Notes を残す必要がある場合は、次の形式を使う。観点ごとの長文レポートは不要。
## Findings
### P1: [タイトル]
- File: `path`
- Lines: N-M
- Category: comments
- Problem: [不正確・誤解を招く点。コードや docs のどこと矛盾するか]
- Impact: [将来の保守者への影響]
- Suggested fix: [具体的な書き換え案または削除理由]
Finding がなく Notes のみある場合:
## Notes
- 未検証: [項目](確認不能な理由)
Finding と Notes の両方がある場合は Findings を先に、続けて Notes を返す。
Finding も Notes もない場合は No findings from comment-analyzer perspective. と1行で返す。
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.
- 9d ago First seen · 102 lines · 37 tokens per session scan A 6f43f338b394
comment-analyzer is a skill published in the GitHub repository kyto64/codex-pr-review-toolkit-minimal (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,327 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 2026-08-31.
Other skills, from other repositories
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
resolve-pr-comments
Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using reasoning recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address PR…
review-code
Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps by running internal reviews and a peer review in parallel and returning combined findings. Single-concern with a type argument, or full review with no argument. Use when the user asks to "review…
assess-technical-debt
Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, and architecture rot. Ranks findings by impact and refactor effort into a report at .turbo/technical-debt.md. Use when the user asks to "assess technical debt", "find technical debt", "review technical…
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…
peer-review
Run an independent peer review via Codex. Use when the user asks to "peer review", "peer review my code", "peer review my plan", "get a second opinion", or "independent review".