task-exec

A task-execution command that plans, carries out, checks, and completes development work using AI agents and supporting agents.

In plain words
What is it for?
It is for coding tasks, especially work that should use TDD (writing tests before or alongside code), Git worktrees, and a final review of the result.
Why use it?
It provides a structured process for detailed planning, verification, testing, and handling problems found during the work.

Command

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 commands/classmethod/tsumiki/task-exec
Clone the repo
git clone --depth 1 https://github.com/classmethod/tsumiki
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 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 $0.00009 $0.00326
Opus 5 $0.00005 $0.00163
Sonnet 5 $0.00002 $0.00065
Haiku 4.5 $0.00001 $0.00033

Measured yesterday against content hash b4bb407832bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-exec 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.

commands/task-exec.md · 14 lines

What it actually says

エージェントやサブエージェントやワークフローを積極的に活用。 opus/sonnet/haiku/fable を利用する 要望を元にして詳細な計画、計画のチェック、実施、実施結果の確認まで実施して完了とする 計画と実施結果の確認とそれ以外の管理はメイン部分で行い、それ以外はサブエージェントに任せる 実施のタスクは計画を検証可能なレベルまで詳細化してから実施する。定期的にチェックを実行し不足が見つかったら差し戻しての再実施を行う。 チェック時に作業的な問題が見つかった場合は問題が起きないように計画の詳細化の実施も検討する コーディング作業は必ずサブエージェントを利用してTDDで行い、最後に計画通りか確認する。不足があれば対処する 作業はgit worktree上で行い。完了時にマージする。完了後はメインのブランチに戻す。不要なworktreeは消す 不明点は解消するまでAskUserQuestionで質問する 詳しく知らない内容はWebにアクセスして確認する

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. yesterday First seen · 14 lines · 9 tokens per session scan A b4bb407832bf

Subscribe to this mod's changes

task-exec is a command published in the GitHub repository classmethod/tsumiki (974 stars, last pushed 25d ago), licensed MIT. It adds 9 tokens to every session and 326 once invoked, about $0.0000 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.