natural-japanese is an Agent Skill that helps write and revise clear, readable Japanese for workplace documents. It supports materials such as meeting minutes, research reports, internal guides, proposals, and blog posts by applying writing rules and checking for formulaic phrasing with SudachiPy-based linting. The catalogue includes instructions, a plugin, and a skill related to this writing workflow.
Borrowing it
Nothing to install: this file belongs to coji/natural-japanese. 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/coji/natural-japanese/main/AGENTS.mdgit clone --depth 1 https://github.com/coji/natural-japaneseWrote 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/coji/natural-japanese/agents-md)<a href="https://agentmods.dev/instructions/coji/natural-japanese/agents-md"><img src="https://agentmods.dev/badge/instructions/coji/natural-japanese/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/coji/natural-japanese/agents-md"><img src="https://agentmods.dev/badge/instructions/coji/natural-japanese/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 | $0.01020 | $0.01020 |
| Opus 5.5 | $0.00408 | $0.00408 |
| Sonnet 5.5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
natural-japanese 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 2d 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
AGENTS.md
このリポジトリは natural-japanese という Agent Skill を配布するためのものです。
スキル本体は skills/natural-japanese/ にあり、SKILL.md と references/・scripts/・assets/ で構成されます。
このスキルについて
仕事の日本語文書を、自然で読みやすく書く・直すためのスキルです。議事録・調査レポート・社内ガイド・リサーチメモ・スライド構成といった仕事の文書から、技術記事・PR の説明文・ブログ・エッセイまで扱います。AI らしい書き癖を取り除くことも含みます。
設計の要点は次の3つです。
- 既存の文書を直すとき、元の文書にない事実・数値・意見・方針は足さない。確信の度合いも変えない。仕上げに、元にない数値・固有名詞・英字の語を
newfacts.pyで洗い出す - 疑わしい箇所の検出は
skills/natural-japanese/scripts/lint.py(sudachipy による形態素解析)が機械的に行い、直すかどうかはエージェントが文脈を見て決める。lint の各指摘には直し方が付いている - 書く前に読み手・主メッセージ・見出しを決め、書くときは SKILL.md §2 の12の原則に沿う
規則と工程はすべて SKILL.md にあります。references/ には、文書タイプ別の型(doctypes/)、診断モードの採点方法(diagnose.md)、lint が使えない環境向けの手順(manual-checklist.md)だけを置いています。
openskills 経由で読み込む場合
npx openskills install coji/natural-japanese
npx openskills sync
npx openskills sync がこの AGENTS.md の中に <available_skills> ブロックを生成し、
Claude Code 以外のエージェント(Cursor, ChatGPT, Codex など)からもこのスキルを利用できるようにします。
検査スクリプトの実行
Python の実行は uv を前提にしています。pip install や仮想環境の手動作成は不要です。主な検査スクリプトは6つあります。
uv run skills/natural-japanese/scripts/lint.py path/to/draft.md # 疑わしい表現の検出。指摘ごとに直し方が付く(--json / --genre / --baseline)
uv run skills/natural-japanese/scripts/outline.py path/to/draft.md # 見出しと各段落の先頭文の抽出(構造の点検に使う)
uv run skills/natural-japanese/scripts/terms.py path/to/draft.md # 専門用語の初出・説明有無の一覧
uv run skills/natural-japanese/scripts/newfacts.py original.md revised.md # 直した文書にだけある数値・固有名詞・英字の語
uv run skills/natural-japanese/scripts/paragraphs.py path/to/draft.md # 段落ごとの確かめ用の表(読み手が何のことか分からない言い回しを、段落ごとに書き出す)
uv run skills/natural-japanese/scripts/calques.py path/to/draft.md # 仕組みを場所にたとえた名詞と、機械の処理に当てた動詞の候補(入口・効く・拾う など)
依存関係(sudachipy, sudachidict-core)は各スクリプト冒頭の PEP 723 インラインメタデータで宣言されているため、
uv run が自動的に解決します。各スクリプトが共通で使う処理は skills/natural-japanese/scripts/textcore.py にまとまっています。
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.
- 2d ago Changed · +14 tokens per session 474d1d5b04f0
- 4d ago Changed · -13 tokens per session 504507354490
- 5d ago Changed · +1 lines · +71 tokens per session 6cd232a6a10f
- 10d ago Changed · +3 lines · +191 tokens per session 25fc96256abf
- 12d ago Changed 0a32dfcdd9be
- 1mo ago Changed · -3 tokens per session 67d11beccc00
- 1mo ago First seen · 39 lines · 760 tokens per session scan A 5b5292cab6ff
natural-japanese AGENTS.md is an instructions file published in the GitHub repository coji/natural-japanese (1,970 stars, last pushed yesterday), licensed MIT. It adds 1,020 tokens to every session, about $0.0041 per session on Opus 5.5. 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 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.