AgentTakt: Instructions file for Claude Code

CLAUDE.md

AgentTakt CLAUDE.md is an instructions file for Claude Code from ryoohshima/AgentTakt. It costs 1,375 tokens per session, scanned A, original, MIT.

Project-specific instructions for Claude Code, an AI coding assistant. They describe AgentTakt, its Python and Textual technology stack, its folders, and its development commands.

In plain words
What is it for?
Use them when working on AgentTakt, especially when navigating its files, running its tools, or following its testing and development workflow.
Why use it?
They give the coding assistant the project context and rules it needs to make changes that fit the existing codebase.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ryoohshima/AgentTakt's own configuration. It tells Claude Code how to work on AgentTakt itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AgentTakt configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ryoohshima/AgentTakt/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ryoohshima/AgentTakt

Made for: Claude Code.

Wrote 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.

agentmods badge for AgentTakt CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ryoohshima/agenttakt/claude-md.svg)](https://agentmods.dev/instructions/ryoohshima/agenttakt/claude-md)
Your own site
<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>
Per session 1,375 This file is loaded in full into every session.
When invoked 1,375 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash c930bb227d00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

CLAUDE.md · 81 lines

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)

Read the full file on GitHub · 81 lines

Changes

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.

  1. 7d ago First seen · 81 lines · 1,375 tokens per session scan A c930bb227d00

Subscribe to this mod's changes

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.

Related

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens