Borrowing it
Nothing to install: this file belongs to First-CH/firstch-tools-mcp. 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/First-CH/firstch-tools-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/First-CH/firstch-tools-mcpWrote 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/first-ch/firstch-tools-mcp/claude-md)<a href="https://agentmods.dev/instructions/first-ch/firstch-tools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/first-ch/firstch-tools-mcp/claude-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/first-ch/firstch-tools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/first-ch/firstch-tools-mcp/claude-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 | $0.00901 | $0.00901 |
| Opus 5.5 | $0.00360 | $0.00360 |
| Sonnet 5.5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
firstch-tools-mcp CLAUDE.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
CLAUDE.md — firstch-tools-mcp
公開リポジトリ。tools.first-ch.com の計算ロジックを MCP サーバー（npm @first-ch/tools-mcp）として配り、同じものを Claude Code の plugin / marketplace（.claude-plugin/marketplace.json・plugins/firstch-tools/）としても配る。社内の情報・人名・内部 URL・内部リポジトリへのパスをこのリポジトリに書かない。
構成
server.mjsが MCP の入口、ツールは1機能1ファイル（*.mjs）。apps.mjsは apps.first-ch.com を呼ぶapp_*ツール（既定で無効）plugins/firstch-tools/.mcp.jsonは npm の版を@first-ch/[email protected]で固定して起動する。plugin 側に実装は置かない- 使い方・ツール一覧・プライバシーの正本は
README.md（英日併記。ツールを足したら両方の表とplugins/firstch-tools/README.mdを直す）
検査（push 前に3つとも緑）とリリース
npm ci && npm test && node e2e.mjs # 単体＋app_* のテスト（ネットワーク不要）、stdio の疎通
.github/workflows/ci.ymlは稼働中: Node 24 でテスト・vendor チェックサム・tarball 内容・版の整合・plugin のピンを検査し、mainへの push が未公開の版なら npm Trusted Publishing で自動公開してvX.Y.Zタグを打つ（README.md「Development」）。手元でnpm publishしない- 版は7か所を同時に上げる:
package.json・package-lock.json（2か所）・server.json（2か所）・plugins/firstch-tools/.claude-plugin/plugin.json・plugins/firstch-tools/.mcp.jsonのピン。1つでも違うと CI が落ちる。server.jsonのdescriptionは100文字以内 - 版を上げずに実装を変えた push は、tarball の内容が違えば CI が止める
FirstCHTools（サイト側）との同期
サイト側（FirstCHTools の site/<tool>/app.js）の実装が正本で、こちらは追従する側。別リポジトリなので CI は相互比較できず、レビュー時の目視と各ファイル冒頭のコメントが頼り。
- アルゴリズムを変える変更はサイト側から始め、同じ変更をこちらに別コミットで反映する（こちらだけ先に変えない）
marp-theme.cssはサイト側のsite/marp/theme-firstch.cssとバイト一致させる（diffで確認。@auto-scaling・@sizeを消さない）openapi-doc.mjs・lines.mjs・wiki-doc-lint.mjsの「ここから〜ここまで」のコアは、サイト側の同名ツールと同一にする（照合コマンドは各ファイル冒頭）vendor/jsquash-webp/はサイト側と同じ@jsquash/webpの版を別々に固定している。片方だけ上げない
触らないもの
vendor/ の配布物は無改変で置き直す（ライセンス文を同梱）。ci.yml の公開ステップと id-token の権限は、変更前に人へ確認する。
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 First seen · 31 lines · 901 tokens per session scan A 8faaa08e0cbc
firstch-tools-mcp CLAUDE.md is an instructions file published in the GitHub repository First-CH/firstch-tools-mcp (0 stars, last pushed today), licensed MIT. It adds 901 tokens to every session, about $0.0036 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 2026-10-30.
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).
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.