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 skills/classmethod/tsumiki/dev-runnpx skills add classmethod/tsumiki --skill dev-rungit clone --depth 1 https://github.com/classmethod/tsumikiWhat 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 | $0.00105 | $0.03454 |
| Opus 5 | $0.00053 | $0.01727 |
| Sonnet 5 | $0.00021 | $0.00691 |
| Haiku 4.5 | $0.00011 | $0.00345 |
Grade A, and why
dev-run 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.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Run
Plan 内の指定範囲タスクに対し、impl → verify → debug のループを自動実行するオーケストレーションスキル。各タスクを Task サブエージェントに委託し、TaskCreate/TaskUpdate で依存関係付きの進捗管理を行う。
前提知識
dev-* スキルフロー内の位置
dev-context → dev-plan → [dev-run] → (完了)
├─ impl サブエージェント (×タスク数)
├─ debug サブエージェント (エラー時)
└─ verify サブエージェント (全タスク完了後)
引数フォーマット
/dev-run <plan-name> <from-task-id> <to-task-id>
plan-name: 既存の Plan 名(docs/dev/plans/<plan-name>/が存在すること)from-task-id: 開始タスク ID(例: "001")to-task-id: 終了タスク ID(例: "005")
サブエージェント制約(重要)
サブエージェントは Task ツールを使用できない(ネスト不可のアーキテクチャ制約)。そのため:
- コード探索は Glob/Grep/Read を直接使用する
- TodoWrite は使用しない(TaskCreate/TaskUpdate で進捗管理する)
- プロンプトに context.md を埋め込み、サブエージェントのファイル読み込みを最小化する
ワークフロー
Step 1: 事前検証とコンテキスト読み込み
docs/dev/context.mdの存在を確認する。存在しない場合は/dev-contextの実行を案内して終了するdocs/dev/plans/<plan-name>/の存在を確認する。存在しない場合は/dev-planの実行を案内して終了するdocs/dev/context.mdを Read で読み込み、以下を抽出する:- テスト実行コマンド(Test Framework セクション)
- ビルドコマンド(Build & Run セクション、あれば)
- Lint コマンド(Build & Run セクション、あれば)
- カバレッジ閾値(Test Framework セクションの Coverage Threshold)
docs/dev/plans/<plan-name>/plan.mdを Read で読み込む- 指定範囲(from-task-id 〜 to-task-id)の全タスクファイルを Glob + Read で読み込む
- 各タスクの
status,dependencies,estimated_complexityを確認する
範囲外依存チェック
タスクファイルの dependencies に、指定範囲外のタスク ID が含まれる場合:
- そのタスクファイルを Read し、
statusを確認する status: done→ 問題なし- それ以外 → AskUserQuestion でユーザーに警告し、続行/中断を確認する
Step 2: TaskCreate で依存関係グラフ構築
2a. タスクの登録
指定範囲内で status が done でないタスクごとに TaskCreate を実行する:
TaskCreate:
subject: "impl-NNN: <タスクタイトル>"
description: "Plan <plan-name> のタスク NNN を TDD 実装する"
activeForm: "Implementing task NNN: <タスクタイトル>"
2b. 依存関係の設定
タスクファイルの dependencies を TaskUpdate の addBlockedBy にマッピングする。
ID マッピングテーブルを構築: {"001": "<TaskCreate_ID>", "002": "<TaskCreate_ID>", ...}
- 範囲内の依存: 対応する TaskCreate ID を blockedBy に設定
- 範囲外の依存(done 済み): blockedBy から除外
status: doneのタスク: TaskCreate しない、依存元からも除外
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.
- 2d ago First seen · 274 lines · 105 tokens per session scan A cceebbdfad60
dev-run is a skill published in the GitHub repository classmethod/tsumiki (974 stars, last pushed 25d ago), licensed MIT. It adds 105 tokens to every session and 3,454 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…