Borrowing it
Nothing to install: this file belongs to himorishige/hatago-mcp-hub. 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/himorishige/hatago-mcp-hub/main/AGENTS.mdgit clone --depth 1 https://github.com/himorishige/hatago-mcp-hubWrote 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/himorishige/hatago-mcp-hub/agents-md)<a href="https://agentmods.dev/instructions/himorishige/hatago-mcp-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/himorishige/hatago-mcp-hub/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/himorishige/hatago-mcp-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/himorishige/hatago-mcp-hub/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 | $0.03694 | $0.03694 |
| Opus 5 | $0.01847 | $0.01847 |
| Sonnet 5 | $0.00739 | $0.00739 |
| Haiku 4.5 | $0.00369 | $0.00369 |
Grade A, and why
hatago-mcp-hub 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS ガイドライン(開発支援用)
このドキュメントは、リポジトリで作業する AI エージェント/開発者向けの運用ガイドです。基本方針、モノレポ構成、テックスタック、開発コマンド、CLI/設定、MCP 準拠要点、設計哲学、リリース運用、ドキュメント方針などを最新の状態でまとめています。
— ドキュメントは日本語(です・ます調)で記載します。技術文書ではキャラクター口調は使用しません。
プロジェクト概要
Hatago MCP Hub は、複数の MCP(Model Context Protocol)サーバーを一元管理する軽量ハブです。Claude Code / Codex CLI / Cursor / Windsurf / VS Code など各種クライアントから、ローカル/NPX/リモートの MCP サーバーへ透過的に接続するための中継点を提供します。設計の核は「薄い実装(最低限の転送・管理に徹する)」です。
テックスタック
- ランタイム: Node.js 20+(Cloudflare Workers 対応: リモートサーバー接続機能中心)
- 言語: TypeScript(ESM, strict)
- Web フレームワーク: Hono(HTTP モード)
- MCP SDK:
@modelcontextprotocol/sdk(Zod ベースの schema 必須) - ビルド: tsdown
- テスト: Vitest
- Lint/Format: ESLint + Prettier(現行の実行スクリプトに準拠)
- パッケージマネージャー: pnpm
補足: 一部ドキュメントに Biome 言及がありますが、現状のルート実行コマンドは ESLint/Prettier を使用します(pnpm lint / pnpm format)。
モノレポ構成
- パッケージマネージャー:
pnpm - 主要ワークスペース(公開想定スコープ:
@himorishige/*)packages/core→@himorishige/hatago-corepackages/runtime→@himorishige/hatago-runtimepackages/transport→@himorishige/hatago-transportpackages/hub→@himorishige/hatago-hubpackages/server→@himorishige/hatago-serverpackages/cli→@himorishige/hatago-clipackages/mcp-hub→@himorishige/hatago-mcp-hub(現行の公開対象)
- その他
examples/: サンプル(Node / Workers)docs/: アーキテクチャ、設定、運用ガイドschemas/: JSON Schema とサンプル設定(schemas/config.schema.json)
参考ツリー(抜粋):
packages/
mcp-hub/ # メイン npm パッケージ(CLI `hatago` 提供)
server/ # HTTP/StreamableHTTP サーバー実装
hub/ # ハブ中核(ルーティング/レジストリ)
core/ # 共通型/定数
runtime/ # 実行時コンポーネント
transport/ # STDIO/HTTP/SSE 等のトランスポート
schemas/
config.schema.json # 設定スキーマ
examples/
node-example/
workers-example/
前提ツール・環境
- Node.js 20 以上(
enginesに準拠) - TypeScript(ESM)
- Lint/Format: ESLint + Prettier(ルートの
eslint.config.js/prettier.config.jsとpnpmスクリプトに準拠)
HTTP モードの追加オプション(計測/ログ):
HATAGO_METRICS=1でインメモリ計測を有効化し/metricsを公開HATAGO_LOG=json(HATAGO_LOG_LEVELに準拠)で JSON ログを有効化
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 · 275 lines · 3,694 tokens per session scan A 947cd7661b58
hatago-mcp-hub AGENTS.md is an instructions file published in the GitHub repository himorishige/hatago-mcp-hub (27 stars, last pushed 12mo ago), licensed MIT. It adds 3,694 tokens to every session, about $0.0185 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 2026-08-30.
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.