Borrowing it
Nothing to install: this file belongs to Sora-bluesky/ja-output-harness. 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/Sora-bluesky/ja-output-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/Sora-bluesky/ja-output-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/sora-bluesky/ja-output-harness/agents-md)<a href="https://agentmods.dev/instructions/sora-bluesky/ja-output-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/sora-bluesky/ja-output-harness/agents-md/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/instructions/sora-bluesky/ja-output-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/sora-bluesky/ja-output-harness/agents-md.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 | $0.01682 | $0.01682 |
| Opus 5 | $0.00841 | $0.00841 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
ja-output-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 9d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ja-output-harness
Codex がこのリポジトリで作業する時に参照する規約。グローバルの
~/.codex/AGENTS.mdに上書きせず、追加の制約として作用する。
このリポジトリについて
ja-output-harness は、OpenAI Codex（CLI / App 両対応）の日本語出力を Codex 公式の Stop hook で品質担保する 暫定ハーネス。既定モード（strict-lite, v0.4.1 以降）では Stop hook が同じターン内で言い直しを発火させる。Codex CLI と Codex App は同じ Rust バイナリを共有し、~/.codex/ 配下の設定を同じ場所から読むため、本ハーネスは両者に同時反映される。OpenAI が Codex 本体に日本語自然化を公式実装した時点で archive する前提で設計されている。詳細は docs/DEPRECATION.md を参照。
技術スタック
- Python 3.11+
- uv で依存管理
mcp[cli]（FastMCP パターン）で MCP サーバー実装pyyamlで設定読み込みpytest+ruffでテスト・Lint
重要ファイル
| パス | 役割 |
|---|---|
src/ja_output_harness/rules.py |
Lint ロジック（純関数） |
src/ja_output_harness/server.py |
FastMCP サーバー。finalize ツールを公開 |
config/banned_terms.yaml |
禁止語・閾値の単一情報源 |
config/agents_rule.md |
ユーザーの ~/.codex/AGENTS.md に追記される品質ゲート規約本文 |
scripts/install.{ps1,sh} |
OS 別インストーラー |
tests/test_rules.py |
単体テスト 28 件 |
tests/fixtures/codex_*.txt |
実 Codex 出力の before/after fixture |
コーディング規約
- すべての lint ルールは
rules.pyの純関数として実装する（副作用なし、入力は(text, cfg)、出力はlist[Violation]） - 新しい禁止語は
config/banned_terms.yamlのbannedに追加する - 新しいルールタイプを追加する場合、
rules.pyにdetect_*関数を追加し、lint()で組み合わせる - テストは fixture ベースで記述、
tests/fixtures/に実データを置く - コミットメッセージは英語（Conventional Commits 準拠）
- CI は pytest matrix（Windows / Linux × Python 3.11 / 3.12）+ gitleaks の 5 チェック必須
ブランチ保護
main は保護されている:
- PR 経由のマージ必須（approval は 0 でも可）
- CI 5 チェック全通過必須
- Linear history 必須（squash / rebase のみ）
- force push / delete 禁止
- Admin は緊急時に bypass 可
つまり、直接 main への push は禁止。feature branch → PR → CI → squash merge の流れを守る。
自分たちの dogfooding
このツール自身が日本語技術文の品質ゲートなので、このリポで作業する Codex の日本語出力も同じルールに従う:
- コード識別子（ファイル名・関数名・変数名・ブランチ名・PR 番号・タスク ID・パラメータ名・コマンド名）は必ずバッククォートで囲む
- 既定の
strict-liteモードではStop hookが自動で検品するため、進捗報告・学習ノート・コミットメッセージ（内容）・PR 説明・リリースノート等は特別な呼び出し無しでそのまま書いてよい。違反があれば Codex が同じターン内で言い直す。strictモードで運用している場合のみmcp__jp_lint__finalizeを明示的に通す - 禁止語（
slice,parity,done,active,ready,squash,dispatch,handoff,regression,fail-close,fast-forward,contract drift）は使わず言い換える - 1 文あたり識別子は 2 個まで、文字数は 80 文字（識別子含む文は 50 文字）以内
- VOICEVOX で音読される場面を想像して書く
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.
- 9d ago First seen · 91 lines · 1,682 tokens per session scan A a511c23de5d6
ja-output-harness AGENTS.md is an instructions file published in the GitHub repository Sora-bluesky/ja-output-harness (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,682 tokens to every session, about $0.0084 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.