Borrowing it
Nothing to install: this file belongs to satoh-y-0323/claude-code-conductor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/satoh-y-0323/claude-code-conductor/main/.claude/skills/codex-review/SKILL.mdgit clone --depth 1 https://github.com/satoh-y-0323/claude-code-conductorWrote 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/satoh-y-0323/claude-code-conductor/codex-review)<a href="https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/codex-review"><img src="https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/codex-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/satoh-y-0323/claude-code-conductor/codex-review"><img src="https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/codex-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 | $0.00303 | $0.01853 |
| Opus 5 | $0.00151 | $0.00927 |
| Sonnet 5 | $0.00061 | $0.00371 |
| Haiku 4.5 | $0.00030 | $0.00185 |
Grade A, and why
codex-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 4d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex-review
.codex/agents/{reviewer_type}.toml のエージェント定義を codex exec のプロンプトに埋め込み、
Codex 自身が code-reviewer / security-reviewer ペルソナとしてレビューを実行する。
2つのモードがある:
- 単一ファイルモード: 指定ファイルを直接レビュー
- ワークフローモード:
git diff HEADの変更差分を対象にレビュー(通常ワークフローの Claude レビューと並走させる想定)
前提確認
Glob で .codex/agents/code-reviewer.toml を確認する。
存在しない場合は以下を表示してスキルを終了する:
[codex-review] Codex アダプターがセットアップされていません。
先に `c3 init --platform codex` を実行してください。
Step 1: モードとレビュー設定を確認する
args を解析する:
"workflow code-reviewer"→ ワークフローモード + code-reviewer"workflow security-reviewer"→ ワークフローモード + security-reviewer"code-reviewer src/path/file.py"→ 単一ファイルモード + code-reviewer"security-reviewer src/path/file.py"→ 単一ファイルモード + security-reviewer
args が不十分な場合、AskUserQuestion でレビュー種別とモードを確認する:
{
"questions": [
{
"question": "実行するレビューの種類を選択してください",
"header": "レビュー種別",
"multiSelect": false,
"options": [
{ "label": "code-reviewer", "description": "品質・保守性・パフォーマンスをレビュー" },
{ "label": "security-reviewer", "description": "OWASP Top 10 基準でセキュリティ脆弱性をレビュー" }
]
},
{
"question": "レビュー対象を選択してください",
"header": "対象",
"multiSelect": false,
"options": [
{ "label": "ワークフロー(git diff)", "description": "現在の変更差分全体をレビュー。通常ワークフローと並走させる場合はこちら" },
{ "label": "単一ファイル", "description": "特定のファイルを指定してレビュー" }
]
}
]
}
単一ファイルモードでファイルパスが未指定の場合:
{
"questions": [{
"question": "レビュー対象のファイルパスを入力してください(「その他」から入力)",
"header": "対象ファイル",
"multiSelect": false,
"options": [
{ "label": "その他(自由入力)", "description": "例: src/c3/cli_ask.py" }
]
}]
}
Step 2: レビュー対象のコンテンツを取得する
ワークフローモードの場合
Bash で以下を実行する:
git diff HEAD --stat
変更ファイルがない場合は git diff HEAD~1 --stat を試す。
それも空の場合は「変更差分が見つかりません。コミット済みの変更を対象にするには git diff HEAD~1 が必要です」と表示して終了する。
続けて差分本体を取得する:
git diff HEAD
差分が長い場合(目安 200 行超)は先頭 200 行に制限する:
git diff HEAD | head -200
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.
- 4d ago First seen · 212 lines · 303 tokens per session scan A a56e5e07ca9f
codex-review is a skill published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed 4d ago), licensed MIT. It adds 303 tokens to every session and 1,853 once invoked, about $0.0015 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 2026-09-04.
Other skills, from other repositories
phase-pr-review-loop
Ship multi-phase engineering work as one-PR-per-phase with plan-first review, adversarial cross-agent code review, per-thread fix verification, and an honest phase status ledger. Use when executing a phased plan across sessions or agents, when asked to review or babysit a PR produced by another agent, when responding…
ho-review
Use when a change has been implemented and someone has to decide whether it is done, whether the reviewer is a different agent with fresh context or the same agent that wrote the code.
verify-change
A change-checking skill that reviews code differences and checks whether related documentation, tests, and records were updated.
verify-quality
A code-quality checker that measures complexity, size, naming, and common code smells. It reports problems such as duplicated code, unused code, and overly long functions.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…