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 instructions/chachamaru127/codex-harness/agents-mdgit 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/instructions/chachamaru127/codex-harness/agents-md)<a href="https://agentmods.dev/instructions/chachamaru127/codex-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/chachamaru127/codex-harness/agents-md.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 | $0.03123 | $0.03123 |
| Opus 5 | $0.01562 | $0.01562 |
| Sonnet 5 | $0.00625 | $0.00625 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
codex-harness AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Codex harness 開発ガイド
このファイルは Codex CLI がこのリポジトリで作業する際の指針です。
プロジェクト概要
Harness は、Codex CLI を「Plan → Work → Review」の型で運用するためのガイドです。
特殊な点: このプロジェクトは「ハーネス自身を使ってハーネスを改善する」自己参照的な構成です。
Codex CLI の前提
- Codex は
.codex/skills/<skill-name>/SKILL.mdを読み込み、$skill-nameで明示呼び出しする - Codex は
AGENTS.override.mdを優先し、次にAGENTS.md、必要なら設定された fallback 名を参照する - Hooks は未対応のため、暫定ガードは
.codex/rules/*.rulesのprefix_rule()で行う
開発ルール
コミットメッセージ
Conventional Commits に従う:
feat:- 新機能fix:- バグ修正docs:- ドキュメント変更refactor:- リファクタリングtest:- テスト追加/更新chore:- メンテナンス
バージョン管理
バージョンは VERSION がソース・オブ・トゥルース。
変更時は ./scripts/sync-version.sh bump を使用。
CHANGELOG 記載ルール（必須）
Keep a Changelog フォーマットに準拠
各バージョンエントリには以下のセクションを使用:
## [X.Y.Z] - YYYY-MM-DD
### Added
- 新機能について
### Changed
- 既存機能の変更について
### Deprecated
- 間もなく削除される機能について
### Removed
- 削除された機能について
### Fixed
- バグ修正について
### Security
- 脆弱性に関する場合
#### Before/After（大きな変更時のみ）
| Before | After |
|--------|-------|
| 変更前の状態 | 変更後の状態 |
セクション使い分け:
| セクション | 使うとき |
|---|---|
| Added | 完全に新しい機能を追加したとき |
| Changed | 既存機能の動作や体験を変更したとき |
| Deprecated | 将来削除予定の機能を告知するとき |
| Removed | 機能やコマンドを削除したとき |
| Fixed | バグや不具合を修正したとき |
| Security | セキュリティ関連の修正をしたとき |
Before/After テーブル: 大きな体験変化（コマンド廃止・統合、ワークフロー変更、破壊的変更）があるときのみ追加。軽微な修正では省略可。
バージョン比較リンク: CHANGELOG.md 末尾に [X.Y.Z]: https://github.com/.../compare/vPREV...vX.Y.Z 形式で追加
コードスタイル
- 明確で説明的な名前を使う
- 複雑なロジックにはコメントを追加
- コマンド/エージェント/スキルは単一責任に保つ
リポジトリ構成
claude-code-harness/
├── codex/ # Codex CLI 配布物
├── commands/ # Claude Code 向けコマンド
├── agents/ # サブエージェント定義（Task tool で並列起動可能）
├── skills/ # エージェントスキル
├── scripts/ # シェルスクリプト（ガード、自動化）
├── templates/ # テンプレートファイル
├── docs/ # ドキュメント
└── tests/ # 検証スクリプト
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.
- 3d ago First seen · 272 lines · 3,123 tokens per session scan A 1f39d2829690
codex-harness AGENTS.md is an instructions file published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 3,123 tokens to every session, about $0.0156 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.