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 skills/chachamaru127/codex-harness/codex-reviewnpx skills add Chachamaru127/codex-harness --skill codex-reviewgit clone --depth 1 https://github.com/Chachamaru127/codex-harnessWrote 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/chachamaru127/codex-harness/codex-review)<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/codex-review"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/codex-review.svg" alt="Measured on agentmods" 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 | $0.00108 | $0.02466 |
| Opus 5 | $0.00054 | $0.01233 |
| Sonnet 5 | $0.00022 | $0.00493 |
| Haiku 4.5 | $0.00011 | $0.00247 |
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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Review Integration Skill
OpenAI Codex CLI を使って Claude Code のコードレビュー時にセカンドオピニオンを提供するスキル。
Do NOT Load For (誤発動防止)
以下のキーワードは /work --codex が担当します:
| トリガーワード | 正しいスキル | 理由 |
|---|---|---|
| "Codex に実装させて" | /work --codex |
実装 ≠ レビュー |
| "Codex Worker" | /work --codex |
Worker = 実装役 |
| "Codex に作らせて" | /work --codex |
作成 = 実装 |
| "実装を依頼" | /work --codex |
実装目的 |
🎯 使用場面
セットアップ
- 初回設定: Codex CLI のインストール確認と MCP 登録
- 認証設定: Codex への OAuth / API キー認証
レビュー
- セカンドオピニオン: Claude のレビュー結果に Codex の視点を追加
- コード品質チェック: 複数 AI モデルの得意分野を活用
- 設計レビュー: アーキテクチャや実装パターンの多角的検証
機能詳細
| 機能 | 詳細 |
|---|---|
| MCP セットアップ | See references/codex-mcp-setup.md |
| レビュー統合 | See references/codex-review-integration.md |
| 4並列レビュー | See references/codex-parallel-review.md |
| モード切替 | See references/codex-mode.md |
実行手順
- ユーザーのリクエストを分類
- 上記の「機能詳細」から適切な参照ファイルを読む
- その内容に従って設定またはレビューを実行
⚠️ 並列レビュー時の必須ルール
Codex モード（review.mode: codex）でのレビュー実行時:
- 呼び出すエキスパートを判定（全部ではなく必要なもののみ）:
- 設定で
enabled: false→ 除外 - CLI/バックエンド → Accessibility, SEO 除外
- ドキュメントのみ変更 → Quality, Architect, Plan Reviewer, Scope Analyst を優先（Security, Performance は除外可）
- 設定で
- 有効なエキスパートの
references/experts/*.mdから プロンプトを個別に読み込む - 有効なエキスパートのみ Bash バックグラウンドプロセスで並列実行
- 絶対に1回の呼び出しで複数観点をまとめない
✅ 正しい（並列 CLI 実行）:
# macOS: brew install coreutils
TIMEOUT=$(command -v timeout || command -v gtimeout || echo "")
$TIMEOUT 120 codex exec "$(cat /tmp/expert-security-prompt.md)" > /tmp/expert-security.txt 2>/dev/null &
$TIMEOUT 120 codex exec "$(cat /tmp/expert-perf-prompt.md)" > /tmp/expert-perf.txt 2>/dev/null &
$TIMEOUT 120 codex exec "$(cat /tmp/expert-quality-prompt.md)" > /tmp/expert-quality.txt 2>/dev/null &
$TIMEOUT 120 codex exec "$(cat /tmp/expert-a11y-prompt.md)" > /tmp/expert-a11y.txt 2>/dev/null &
wait
❌ 間違い:
codex exec "セキュリティとパフォーマンスと品質をレビューして"
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CLAUDE.md 347 B
- references/CLAUDE.md 1.2 KB
- references/codex-mcp-setup.md 6.6 KB
- references/codex-mode.md 2.5 KB
- references/codex-parallel-review.md 16 KB
- references/codex-review-integration.md 4.3 KB
- references/experts/_shared-constraints.md 848 B
- references/experts/acceptance-expert.md 1.6 KB
- references/experts/accessibility-expert.md 1.4 KB
- references/experts/architect-expert.md 1.7 KB
- references/experts/clarity-expert.md 1.2 KB
- references/experts/CLAUDE.md 673 B
- references/experts/dependencies-expert.md 1.5 KB
- references/experts/feasibility-expert.md 1.4 KB
- references/experts/impact-expert.md 1.8 KB
- references/experts/performance-expert.md 1.6 KB
- references/experts/plan-reviewer-expert.md 1.9 KB
- references/experts/priority-expert.md 1.5 KB
- references/experts/quality-expert.md 1.5 KB
- references/experts/scope-analyst-expert.md 2.2 KB
- references/experts/scope-creep-expert.md 1.6 KB
- references/experts/scope-feasibility-expert.md 1.6 KB
- references/experts/security-expert.md 1.5 KB
- references/experts/seo-expert.md 1.6 KB
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 · 240 lines · 108 tokens per session scan A e355c150a809
codex-review is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 108 tokens to every session and 2,466 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…