Borrowing it
Nothing to install: this file belongs to shogo-hs/guidepost-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/shogo-hs/guidepost-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/shogo-hs/guidepost-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/shogo-hs/guidepost-mcp/claude-md)<a href="https://agentmods.dev/instructions/shogo-hs/guidepost-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shogo-hs/guidepost-mcp/claude-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 5.1 | $0.01931 | $0.01931 |
| Opus 5 | $0.00966 | $0.00966 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
guidepost-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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — guidepost-mcp
案内の樹形図（flows/*.yaml）を MCP 経由で辿らせるサーバー。エージェントが回答のラベルを
投げると、次に何を確認・案内すべきかがルールベースで返る。端まで辿れば案内完了。
利用者は自己ループ型の CS エージェント（LiveKit + LangGraph の音声エージェント）だが、 樹形図の語彙をドメインに依存させていないので、手続きを順に進める仕事全般に使える。
Python 3.11+ / uv / ruff / mypy strict / pytest。FastAPI + MCP 同居、ポート 8127。
コマンド
| 用途 | コマンド |
|---|---|
| 依存インストール | uv sync |
| テスト | uv run pytest -q（CI と同じにするなら -m "not perf"） |
| レイテンシ計測 | uv run pytest -m perf（性能の分かっている機体でだけ意味がある） |
| lint・型検査 | uv run ruff check . && uv run ruff format --check . && uv run mypy src |
| 樹形図の検証 | uv run guidepost-mcp lint flows/ |
| 樹形図を木で表示 | uv run guidepost-mcp show payment_failed --flows flows |
| 預かった草案の一覧 | uv run guidepost-mcp drafts |
| 草案を承認して正本にする | uv run guidepost-mcp approve <flow_id>（discard で捨てる） |
| 起動 | uv run uvicorn guidepost_mcp.web:app --host 127.0.0.1 --port 8127 |
| MCP の煙試験 | uv run python scripts/mcp_smoke.py（--parallel で 2 本同時） |
環境変数は GP_DATA_DIR / GP_FLOWS_DIR / GP_PORT / GP_ENABLE_MCP /
GP_PUBLIC_BASE_URL / GP_BUSY_TIMEOUT_MS / GP_DRAFTS_DIR（src/guidepost_mcp/config.py）。
モジュール
| モジュール | 役割 |
|---|---|
models.py |
Flow / Node / Slot の型と YAML 読み込み。kind ごとの正規化（読めるかどうかまで） |
engine.py |
遷移の判定。DB に触らない純関数。advance（埋まっている分だけ前進）/ fold（枝を畳む）/ distances |
store.py |
SQLite。runs / values / steps の3テーブル |
registry.py |
樹形図のメモリ常駐と距離のキャッシュ |
config.py |
環境変数（GP_*） |
lint.py |
樹形図の構造検証（読めるが構造がおかしいもの） |
cli.py |
lint / show / drafts / approve / discard |
drafts.py |
草案の保管だけ（書く・並べる・正本へ移す・消す）。lint は呼び出し側の仕事 |
mcp_server.py |
guide_* 7本 |
layout.py |
樹形図の SVG（自前レイアウト） |
web.py |
FastAPI。一覧・詳細・API・/mcp のマウント |
樹形図のスキーマ
ノードは ask（確認して分岐）/ tell（案内する）/ collect（順不同で集める）/ end（終端）の4種。
flows/payment_failed.yaml が全機能を使っているので、書き方はそれを見る。
category は必須。 flows/categories.yaml に定義したカテゴリ名だけを名乗れる
（lint が error で止める）。フロー id は英数字・アンダースコア・ハイフンだけにする
（id はそのまま flows/<id>.yaml と草案のファイル名になる。これも lint が止める）。
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.
- 5d ago First seen · 96 lines · 1,931 tokens per session scan A 1a97fbba3d55
guidepost-mcp CLAUDE.md is an instructions file published in the GitHub repository shogo-hs/guidepost-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 1,931 tokens to every session, about $0.0097 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.
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.