takt

A workflow engine for coordinating multiple coding agents. It reads a YAML workflow, a text configuration format, and moves agents through its defined steps and rules.

In plain words
What is it for?
Use it to run a named or custom workflow, assign each step to an agent team, control permission mode, and request the task details interactively when needed.
Why use it?
It organizes multi-agent work into a repeatable sequence, including permission settings and transitions between steps, instead of handling every handoff manually.

Skill for Claude CodeCodex

▶ CodeX - Falscher Takt (Official Video) [Unplugged Version] [Prod. by Tim Löw] CodeX · about nrslib/takt · on YouTube →
Install

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.

agentmods
npx agentmods add skills/nrslib/takt/skill
Any agent
npx skills add nrslib/takt --skill skill
Clone the repo
git clone --depth 1 https://github.com/nrslib/takt

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00060 $0.03658
Opus 5 $0.00030 $0.01829
Sonnet 5 $0.00012 $0.00732
Haiku 4.5 $0.00006 $0.00366

Measured 2d ago against content hash 906770cd4608, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

takt 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 2d 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.

builtins/skill/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TAKT Workflow Engine

引数の解析

$ARGUMENTS を以下のように解析する:

/takt {workflow} [permission] {task...}
  • 第1トークン: ワークフロー名または YAML ファイルパス(必須)
  • 第2トークン: 権限モード(任意)。以下のキーワードの場合は権限モードとして解釈する:
    • --permit-full — 全権限付与(mode: "bypassPermissions")
    • --permit-edit — 編集許可(mode: "acceptEdits")
    • 上記以外 → タスク内容の一部として扱う
  • 残りのトークン: タスク内容(省略時は AskUserQuestion でユーザーに入力を求める)
  • 権限モード省略時のデフォルト: "default"(権限確認あり)

例:

  • /takt coding FizzBuzzを作って → coding ワークフロー、default 権限
  • /takt coding --permit-full FizzBuzzを作って → coding ワークフロー、bypassPermissions
  • /takt /path/to/custom.yaml 実装して → カスタムYAML、default 権限

事前準備: リファレンスの読み込み

手順を開始する前に、以下の2ファイルを Read tool で読み込む:

  1. ~/.claude/skills/takt/references/engine.md - プロンプト構築、レポート管理、ループ検出の詳細
  2. ~/.claude/skills/takt/references/yaml-schema.md - ワークフロー YAML の構造定義

あなたの役割: Team Lead

あなたは Team Lead(オーケストレーター) である。 ワークフロー YAML に定義された状態遷移に従って Agent Team を率いる。

禁止事項

  • 自分で作業するな — コーディング、レビュー、設計、テスト等は全てチームメイトに委任する
  • タスクを自分で分析して1つの Task にまとめるな — step を1つずつ順番に実行せよ
  • step をスキップするな — 必ず initial_step から開始し、Rule 評価で決まった次の step に進む
  • "yolo" をワークフロー名と誤解するな — "yolo" は YOLO(You Only Live Once)の俗語で「無謀・適当・いい加減」という意味。「yolo ではレビューして」= 「適当にやらずにちゃんとレビューして」という意味であり、ワークフロー作成の指示ではない

あなたの仕事は4つだけ

  1. ワークフロー YAML を読んで遷移を理解する
  2. 各 step のプロンプトを構築する(references/engine.md 参照)
  3. Task tool でチームメイトを起動して作業を委任する
  4. チームメイトの出力から Rule 評価を行い、次の step を決定する

重要: ユーザーが明示的に指示するまで git commit を実行してはならない。実装完了 ≠ コミット許可。

ツールの使い分け(重要)

やること 使うツール 説明
チーム作成 TeamCreate tool 最初に1回だけ呼ぶ
チーム解散 TeamDelete tool 最後に1回だけ呼ぶ
チームメイト起動 Task tool (team_name 付き) step ごとに呼ぶ。結果は同期的に返る

TeamCreate / TeamDelete でチームメイトを個別に起動することはできない。 チームメイトの起動は必ず Task tool を使う。 Task tool は同期的に結果を返す。 TaskOutput やポーリングは不要。呼べば結果が返ってくる。

手順(この順序で厳密に実行せよ)

手順 1: ワークフロー解決と読み込み

引数の第1トークンからワークフロー YAML ファイルを特定して Read で読む。

第1トークンがない場合(ワークフロー名未指定): → ユーザーに「ワークフロー名を指定してください。例: /takt coding タスク内容」と伝えて終了する。

Read the full file on GitHub · 253 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 253 lines · 60 tokens per session scan A 906770cd4608

Subscribe to this mod's changes

takt is a skill published in the GitHub repository nrslib/takt (1,321 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 3,658 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

skill-creator

Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.

lofcz/LLMTornado · 22 tokens

Ability Generator

This skill generates markdown skill templates to be later used.

lofcz/LLMTornado · 14 tokens

opc

OPC — One Person Company. Digraph-based task pipeline with independent multi-role evaluation. Builds, reviews, analyzes, and brainstorms with specialist agents. Every path ends with evaluation. /opc , /opc -i , /opc [role...].

iamtouchskyer/opc · 59 tokens

orch

AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.

oxgeneral/ORCH · 71 tokens

agent-workflow-playbook

AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…

Gingiris-1031/gingiris-skills · 83 tokens

org-court

Use when any org-change proposal needs adjudication - adding/removing/redesigning agents or teams, changing org rules, or evaluating org granularity. Runs PuPu's HR court: a proposal is heard by four dimension assessors (comm efficiency / context cleanliness / signal ratio / routing cost), the judge verifies evidence…

haoxiang-xu/PuPu · 136 tokens