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/masa-san-jp/agent-aiko/codexnpx skills add masa-san-jp/Agent-Aiko --skill codexgit clone --depth 1 https://github.com/masa-san-jp/Agent-AikoWrote 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/masa-san-jp/agent-aiko/codex)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/codex"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/codex.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 5.1 | $0.00121 | $0.01045 |
| Opus 5 | $0.00060 | $0.00522 |
| Sonnet 5 | $0.00024 | $0.00209 |
| Haiku 4.5 | $0.00012 | $0.00104 |
Grade A, and why
codex 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 5d 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
/codex
Agent-team 共通スキル。codex app-server 経由で ChatGPT サブスクリプションに問い合わせる。実装本体は {{ORG_REPO_PATH}}/Agent-team/tools/codex/。
サブコマンド
| 形 | 用途 |
|---|---|
/codex setup |
初回セットアップ（Codex CLI インストール＋ OAuth ログイン） |
/codex ask <prompt> |
1 ターン質問。応答テキストを返す |
/codex status |
認証状態とアカウント情報を表示 |
/codex |
引数なしの場合は status と同等 |
実行手順
setup
bash {{ORG_REPO_PATH}}/Agent-team/tools/codex/setup.sh
冪等。既にログイン済みならスキップ。失敗時は表示メッセージに従う。
ask
{{ORG_REPO_PATH}}/Agent-team/tools/codex/codex-ask "<prompt>"
- ストリーミング出力したい場合：
CODEX_STREAM=1 {{ORG_REPO_PATH}}/Agent-team/tools/codex/codex-ask "<prompt>" - モデル指定：
CODEX_MODEL=<slug> {{ORG_REPO_PATH}}/Agent-team/tools/codex/codex-ask "<prompt>" - デバッグ：
CODEX_DEBUG=1で App Server の stderr を表示 - 失敗時の終了コード：
1=実行時エラー /2=引数不足 /3=未認証（setup を案内）
前提：Codex CLI 0.128.0+ が必要。古い場合は npm update -g @openai/codex。
出力の取り扱い（重要）
- ChatGPT の応答は 「ChatGPT による応答」と明示 したうえでユーザー or 上位エージェントに報告
- Claude 自身の見解と混在させない（出典明示の原則）
- 機密情報・社内データはプロンプトに含めない（OpenAI に送信されるため）
いつ使うか
クイックルーティング判断表
| タスク性質 | 推奨 | 理由 |
|---|---|---|
| 不可逆判断の第二意見 | Codex (/codex ask) |
モデルの多様性で死角を補完 |
| 技術トレンド並列調査 | Codex (/codex ask) |
Claude+ChatGPT 両視点の合成 |
| 定型コード生成・複数言語実装 | Codex (/codex ask) |
仕様→生成→Claude レビューの分業 |
| アーキテクチャ・設計判断 | Claude（自分） | 自己検証ループ、コンテキスト保持 |
| セキュリティ審査・競合状態分析 | Claude（自分） | 深い脆弱性推論は Claude が有利 |
| ドキュメント生成 | Claude（自分） | コンテキスト連続性が必要 |
| 機密データ・社内情報含む | Claude（自分） | Codex 絶対不可（OpenAI に送信） |
判断基準の詳細は workflow-templates/ の codex_* パターンスキル参照（このパッケージには含まれない、各組織で必要に応じて追加）。
制約
- 機密情報送信禁止：社内固有名詞・人名・契約情報・案件名はプロンプトに含めない
- 出典明示：ChatGPT 応答は必ず「ChatGPT による応答」と明示
- 混在禁止：Claude の見解と ChatGPT の応答を混ぜない
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.
- 5d ago First seen · 69 lines · 121 tokens per session scan A e9b1e7ef5881
codex is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,045 once invoked, about $0.0006 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
canvas
Display HTML content — games, visualizations, dashboards, generated HTML, interactive demos — on a connected canvas-capable display surface. Use when you need to present visual or interactive web content on a screen.
share-skills
Use when you need to author, package, or share a skill folder — understanding the SKILL.md format, where skills live, and how to bundle a folder so it can be shared with others.
git-commit
Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
optimizer
Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.
app_evaluator
A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).