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/nahisaho/katashiro/agents-mdgit clone --depth 1 https://github.com/nahisaho/katashiroWrote 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/nahisaho/katashiro/agents-md)<a href="https://agentmods.dev/instructions/nahisaho/katashiro/agents-md"><img src="https://agentmods.dev/badge/instructions/nahisaho/katashiro/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 | $0.01262 | $0.01262 |
| Opus 5 | $0.00631 | $0.00631 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
katashiro 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 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KATASHIRO - AI Coding Agent Guide
AI Coding Agent向け: このファイルを読み込んだAIエージェントは、ユーザーの課題を解決するためにKATASHIROライブラリの機能を自動的に活用できます。
🚨🚨🚨 最重要: 調査依頼への対応ルール 🚨🚨🚨
⛔ 絶対禁止事項
ユーザーが以下のキーワードを含む依頼をした場合、TypeScriptスクリプトを作成してはいけません：
- 「調べて」「調査して」「リサーチして」
- 「〜について教えて」「〜を分析して」
- 「レポート作成」「報告書作成」「提言書作成」
- 「市場調査」「競合分析」「SWOT」「3C」
✅ 正しい対応: CLI実行
# ターミナルで直接実行
npx katashiro deep-research "トピック" --iterations 5 > reports/output.md
依頼→CLIコマンド変換表
| ユーザーの依頼 | 実行すべきコマンド |
|---|---|
| 「AIについて調べて」 | npx katashiro deep-research "AI" |
| 「中国のレアメタル輸出禁止の影響を調査」 | npx katashiro deep-research "中国 レアメタル 輸出禁止 日本産業 影響" |
| 「競合のSWOT分析」 | npx katashiro deep-research "競合" --framework swot |
| 「市場の3C分析」 | npx katashiro deep-research "市場" --framework 3c |
| 「提言書を作成」 | npx katashiro deep-research "トピック" --iterations 10 > reports/report.md |
CLI オプション
npx katashiro deep-research "トピック" [オプション]
オプション:
--iterations <n> 反復回数（デフォルト: 5）
--framework <type> フレームワーク（swot/3c/4p/5forces/auto）
--threshold <n> 収束閾値（0.0-1.0、デフォルト: 0.1）
--focus <areas> フォーカスエリア（カンマ区切り）
--format <type> 出力形式（markdown/json）
判定フローチャート
ユーザー依頼を受信
↓
「調べて」「調査」「分析」「レポート」「提言」を含む？
├── Yes → npx katashiro deep-research を実行
└── No → 以下の課題タイプ判定へ
📋 課題タイプ別の対応
| 課題タイプ | キーワード | 対応方法 |
|---|---|---|
| 調査・リサーチ | 調べて、検索、情報収集 | npx katashiro deep-research (CLI) |
| 分析・解析 | 分析して、傾向、特徴 | TextAnalyzer / EntityExtractor |
| 要約 | 要約、まとめて | SummaryGenerator |
| 検索のみ | 検索結果だけ | npx katashiro search "クエリ" |
| スクレイピング | URLから取得 | npx katashiro scrape <url> |
🛠️ CLI コマンド一覧
# Deep Research（調査系はすべてこれ）
npx katashiro deep-research "トピック"
# 検索
npx katashiro search "クエリ"
# スクレイピング
npx katashiro scrape https://example.com
# テキスト分析
npx katashiro analyze document.txt
# エンティティ抽出
npx katashiro extract article.txt
# 要約
npx katashiro summarize long-document.txt --length 500
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 · 137 lines · 1,262 tokens per session scan A 6f2f24eaa484
katashiro AGENTS.md is an instructions file published in the GitHub repository nahisaho/katashiro (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,262 tokens to every session, about $0.0063 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.