Borrowing it
Nothing to install: this file belongs to ryoohshima/AgentTakt. 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/ryoohshima/AgentTakt/main/CLAUDE.mdgit clone --depth 1 https://github.com/ryoohshima/AgentTaktWrote 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/ryoohshima/agenttakt/claude-md)<a href="https://agentmods.dev/instructions/ryoohshima/agenttakt/claude-md"><img src="https://agentmods.dev/badge/instructions/ryoohshima/agenttakt/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 | $0.01375 | $0.01375 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
AgentTakt 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 7d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
プロジェクト固有の Claude Code 指示
このファイルは本プロジェクトに固有のルール・コンテキストを Claude Code に伝えるためのものでござる。
全プロジェクト共通のガイドラインは ~/.claude/CLAUDE.md に記載されており、本ファイルはそれを補完する形で記述するでござる。
プロジェクト概要
AgentTakt — AI エージェント(Executor)が MCP 経由で送信したタスク実行計画 JSON を、人間がターミナル上の ComfyUI 風ビジュアルノードエディタでレビュー・編集・承認する MCP サーバー兼 TUI ツール。
- MCP サーバー(
agenttakt serve)と TUI 常駐プロセス(agenttakt)の 2 プロセス構成。Unix domain socket(NDJSON)で接続する(詳細は docs/architecture.md) - 親 issue: #3(M0〜M4 + docs の sub-issue で進捗管理)
技術スタック
- 言語: Python 3.10+(開発環境は 3.12)
- TUI: Textual >= 8.2
- MCP: Python MCP SDK v1 FastMCP(
mcp>=1.9,<2にピン留め。SDK import はsrc/agenttakt/server/mcp_server.pyに閉じ込める) - データモデル: pydantic v2
- パッケージマネージャ: uv(build backend は hatchling、src レイアウト)
ディレクトリ構成
.
├── src/agenttakt/
│ ├── cli.py # エントリポイント(agenttakt / at)
│ ├── models/ # Plan データモデル・DAG 検証・自動レイアウト
│ ├── bridge/ # socket プロトコル・クライアント・サーバー
│ ├── server/ # MCP サーバー(SDK import はここのみ)
│ └── tui/ # Textual アプリ(screens / widgets / geometry)
├── tests/ # pytest(モデル・プロトコル・Pilot による TUI テスト)
├── examples/ # デバッグモード用サンプル計画 JSON
├── docs/ # ユーザー向けドキュメント(dev/ 配下は開発者向け設計資料)
└── tasks/ # Claude Code 作業記録(todo.md / lessons.md)
開発コマンド
# セットアップ
uv sync
# 実行
uv run agenttakt # TUI 常駐起動
uv run agenttakt serve # MCP stdio サーバー
uv run agenttakt open examples/sample_plan.json # デバッグモード(MCP なし)
# テスト
uv run pytest
# TUI 開発(textual devtools)
uv run textual console # 別ターミナルでログ閲覧
uv run textual run --dev src/agenttakt/tui/app.py
ドッグフーディング(AgentTakt 自身を使う)
本リポジトリは .mcp.json で開発版の AgentTakt(uv run agenttakt serve)を MCP サーバーとして登録している。自分の道具は自分で使うこと。
- 3 ステップ以上の作業計画を立てたら、着手前に
show_plan(plan, summary)でノードグラフとして提示する(プランモードに限らない) - 不可逆な作業(リリース・スキーマ変更・広範なリファクタ)は
request_approval(plan, summary)で承認を得てから着手する - plan JSON の形式は docs/schema.md を参照
- TUI が起動していないとツールはエラーを返す。その場合は別ターミナルで
uv run agenttaktを起動するようユーザーに依頼する(勝手に起動しない) - 使いにくさ・表示の不備に気づいたら issue に残す(ドッグフーディングは実運用検証を兼ねる)
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.
- 7d ago First seen · 81 lines · 1,375 tokens per session scan A c930bb227d00
AgentTakt CLAUDE.md is an instructions file published in the GitHub repository ryoohshima/AgentTakt (0 stars, last pushed 9d ago), licensed MIT. It adds 1,375 tokens to every session, about $0.0069 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
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).
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.
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).
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.