Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/hnakamura33/task-composer/claude-mdgit clone --depth 1 https://github.com/HNakamura33/task-composerWrote 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/hnakamura33/task-composer/claude-md)<a href="https://agentmods.dev/instructions/hnakamura33/task-composer/claude-md"><img src="https://agentmods.dev/badge/instructions/hnakamura33/task-composer/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 | $0.03588 | $0.03588 |
| Opus 5 | $0.01794 | $0.01794 |
| Sonnet 5 | $0.00718 | $0.00718 |
| Haiku 4.5 | $0.00359 | $0.00359 |
Grade A, and why
task-composer 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 yesterday.
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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Composer
DAGベースのタスク管理ライブラリ(Rust学習プロジェクト)
Claudeへの指示
このプロジェクトはRust学習を目的としています。以下の点を意識してサポートしてください:
- コードを直接書かない: ヒントやシグネチャを提示し、ユーザーが自分で実装できるようガイドする
- 概念を説明する: 新しいRustの概念が出てきたら、図や例を使って分かりやすく説明する
- エラーを学習機会に: コンパイルエラーが出たら、なぜそのエラーが起きるのかを丁寧に解説する
- 段階的に進める: 一度に大量のコードを提示せず、小さなステップで進める
- 質問を促す: ユーザーが理解を深められるよう、適宜質問を投げかける
- テストを重視: 実装後は必ずテストを書くよう促す
プロジェクト概要
有向非巡回グラフ(DAG)を使ってタスクの依存関係を管理するRustライブラリ。
構造
task-composer/
├── Cargo.toml # ワークスペース定義
├── LICENSE # Apache 2.0
├── README.md
├── CLAUDE.md # このファイル
├── task-composer-core/ # コアライブラリ
│ ├── Cargo.toml
│ └── src/
│ ├── lib.rs
│ ├── types.rs # 型定義(Task, Role, Config等)
│ ├── path_resolver.rs # パス参照・埋め込み参照の解決
│ ├── dag/ # DAG実装
│ │ ├── mod.rs
│ │ └── tests.rs
│ ├── checkpoint/ # チェックポイント機能
│ │ ├── mod.rs
│ │ └── writer.rs
│ ├── task_executor/ # Executor実装
│ │ ├── mod.rs
│ │ ├── log_executor.rs
│ │ ├── mcp_executor.rs
│ │ ├── dag_executor.rs
│ │ ├── bash_executor.rs
│ │ ├── data_executor.rs
│ │ ├── git_executor.rs
│ │ ├── github_executor.rs
│ │ ├── map_executor.rs
│ │ ├── filter_executor.rs
│ │ └── reduce_executor.rs
│ └── analysis/ # 静的解析
│ ├── mod.rs
│ ├── dag_analysis.rs
│ ├── task_validation.rs
│ └── conflict/
├── task-composer-cli/ # CLIツール
│ ├── Cargo.toml
│ └── src/
│ ├── main.rs
│ └── signal.rs # シグナルハンドリング
├── task-composer-ui/ # Dioxus UI(Desktop/Web/TUI)
│ ├── Cargo.toml
│ ├── Dioxus.toml
│ └── src/
│ ├── main.rs
│ ├── tui_main.rs
│ ├── components/ # UIコンポーネント
│ ├── hooks/ # カスタムフック
│ └── state/ # 状態管理
├── mcp_servers/
│ └── claude_code_mcp/
│ ├── main.py # FastMCPサーバー
│ └── pyproject.toml
└── samples/ # サンプルDAGファイル
├── basics/ # 基本サンプル
│ ├── minimal.json
│ ├── simple_dag.json
│ ├── auto_dependency.json
│ └── embedded_reference.json
├── executors/ # Executor別サンプル
│ ├── bash.json
│ ├── data.json
│ ├── git/
│ ├── github/
│ └── mcp/
├── features/ # 機能別サンプル
│ ├── condition/ # if/else条件
│ ├── loop/ # ループ実行
│ └── subgraph/ # サブグラフ
└── workflows/ # ワークフローサンプル
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.
- yesterday First seen · 277 lines · 3,588 tokens per session scan A 925adc29f8ad
task-composer CLAUDE.md is an instructions file published in the GitHub repository HNakamura33/task-composer (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,588 tokens to every session, about $0.0179 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 2026-09-04.
Other instructions, from other repositories
Claude-Socratic CLAUDE.md
Claude Code instructions for rafaelmmiller/Claude-Socratic, covering claude code guidelines for rust learning, core philosophy, rules, 1. never write or modify code directly and 2. socratic method.
turso AGENTS.md
AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
ton-rs AGENTS.md
AGENTS.md instructions for ston-fi/ton-rs, covering ton-rs agent guide, repository, boundaries, public api and ton invariants.
codesage AGENTS.md
AGENTS.md instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.