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 atman-33/workhub --skill persona-reviewgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/persona-review)<a href="https://agentmods.dev/skills/atman-33/workhub/persona-review"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/persona-review/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/atman-33/workhub/persona-review"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/persona-review.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 | $0.00047 | $0.00854 |
| Opus 5 | $0.00023 | $0.00427 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
persona-review 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 10d 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.
What it actually says
Derived from genshijin (MIT, InterfaceX-co-jp) — https://github.com/InterfaceX-co-jp/genshijin
レビューコメントは簡潔かつ行動可能に。1行1指摘。位置・問題・修正。前置き禁止。
このスキルはキャラクター非依存。 レビューコメントは PR に残る文章なので、 どのキャラクターが有効でも口調を適用しない。
形式
L<line>: <問題>。<修正>。 — 複数ファイルにまたがる場合は <file>:L<line>: ...
重大度プレフィックス
- 🔴
バグ:— 壊れている。インシデントに直結する - 🟡
リスク:— 動くが脆い（race、null 未チェック、握り潰した error） - 🔵
nit:— スタイル・命名・ミクロ最適化。著者は無視してよい - ❓
質問:— 純粋な疑問。提案ではない
削除する
- 「〜に気づきました」「〜のように見えます」「〜を検討するとよいかもしれません」
- 「あくまで提案ですが」→
nit:を使う - 「素晴らしい仕事です」「全体的には良さそうですが」— 先頭に一度だけ。個別コメントには不要
- その行が何をしているかの説明 — diff を読めば分かる
- ぼかし（「おそらく」「たぶん」「〜と思います」）— 不確実なら
質問:にする
保持する
- 正確な行番号
- シンボル・関数名・変数名はバッククォートで囲む
- 具体的な修正案（「リファクタリングを検討」は不可）
- 問題文から自明でない「なぜ」
例
不可:
L42 で user オブジェクトが null かどうかをチェックせずに email プロパティに アクセスしているように見えます。DB で user が見つからなかった場合にクラッシュする 可能性があります。null チェックを追加することを検討してみてください。
可:
L42: 🔴 バグ: .find() 後 user が null になりうる。.email の前にガードを追加。
L88-140: 🔵 nit: 50行の関数に4責務。validate / normalize / persist を抽出。
L23: 🟡 リスク: 429 のリトライなし。withBackoff(3) で包む。
簡潔モードを解除するケース
以下は通常の段落で記述する。該当の指摘が終わったらすぐ形式に戻る。
- セキュリティ指摘（CVE 級は参照 URL 付きで十分な説明が必要）
- アーキテクチャへの異論（根拠が必要。ワンライナーでは不足）
- 新人のオンボーディング文脈（「なぜ」が必要）
境界
- レビューのみ。コード修正、approve / request-changes、linter の実行はしない
- 出力はそのまま PR に貼り付けられる形式にする
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.
- 10d ago First seen · 69 lines · 47 tokens per session scan A 9ec39ea31e85
persona-review is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 854 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
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.