TAKT is a command-line workflow engine for coordinating AI coding agents through defined planning, implementation, review, and repair steps. Development teams describe agent roles, permissions, checkpoints, and outputs in YAML, while TAKT runs tasks in isolated worktrees and records their results; the catalogue entries provide agents, instructions, and skills for these workflows.
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 skills add nrslib/takt --skill skill-codexgit clone --depth 1 https://github.com/nrslib/taktWrote 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/skills/nrslib/takt/skill-codex)<a href="https://agentmods.dev/skills/nrslib/takt/skill-codex"><img src="https://agentmods.dev/badge/skills/nrslib/takt/skill-codex/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nrslib/takt/skill-codex"><img src="https://agentmods.dev/badge/skills/nrslib/takt/skill-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 155 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 156 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00063 | $0.03382 |
| Opus 5.5 | $0.00025 | $0.01353 |
| Sonnet 5.5 | $0.00013 | $0.00676 |
| Haiku 4.5 | $0.00006 | $0.00338 |
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 1mo 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 — 210 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-codex exec --sandbox danger-full-access--permit-edit-codex exec --full-auto- 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(codex exec (オプションなし))
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、danger-full-access$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:
~/.agents/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~/.agents/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 step を実行する。
禁止事項
- 自分で作業するな - コーディング、レビュー、設計、テスト等は全てサブエージェントに委任する
- タスクを自分で分析して1つの実装にまとめるな - 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
- ワークフロー YAML を読んで遷移を理解する
- 各 step のプロンプトを構築する(references/engine.md 参照)
- Write tool + Bash tool (
codex exec) でサブエージェントを起動して作業を委任する - サブエージェントの出力から 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 |
|---|---|---|
| プロンプト一時保存 | Write tool | step 名を含めない安全なランダム名(例: /tmp/takt-prompt-{timestamp}-{uuid}.md)で書き出す |
| サブエージェント起動 | Bash tool | codex exec {権限オプション} - < /tmp/... を実行 |
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。
ワークフロー YAML の検索順序:
.yaml/.ymlで終わる、または/を含む → ファイルパスとして直接 Read- 名前解決:
~/.takt/workflows/{name}.yaml(ユーザーカスタム、優先)~/.agents/skills/takt/workflows/{name}.yaml(Skill 同梱ビルトイン)
- 見つからない場合: 上記ディレクトリを Glob で列挙し、AskUserQuestion で選択させる
What ships with it
3 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.
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.
- 1mo ago First seen · 210 lines · 63 tokens per session scan A cae4acb13ce9
takt is a skill published in the GitHub repository nrslib/takt (1,409 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 3,382 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
stage-assemble
How to execute a validated, currently authorized project/plan.json into one finished file. Start/resume with production.status; if planapprovalcurrent is false, pass the state to gate-control and stop instead of producing or opening child gates. Walk the signed EDL; do not re-plan. Host-neutral: VideoStudio-specific…
stage-plan
How to turn "here is my material + here's the video I want" into a single, inspectable plan that spans reference images, reference videos, deterministic editing, semantic editing, generation, and composition. The output is project/plan.json — a cross-modal Edit Decision List (EDL) — which the assembler walks.…
ppt-review
Read this skill before the first deck or output quality review, so its criteria are available when the rendered images arrive. Apply the criteria to current officereview structural output and relevant rendered images. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck…
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML or other UI source code, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live source runtime.
image-compose
Read this skill after route lock for COMPOSE, or later in HYBRID, GENERATE, or EDIT only when deterministic copy, layout, diagram, framing, crop, mask, or overlay work is required. Do not preload it during routing. Keep the artifact in one stable directory containing image-manifest.json, index.html, and local assets.
design-system-importer
Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.