agentmods.dev

dev-plan

A development-planning tool that turns a feature request or product-requirements document into a design and a list of testable tasks. It supports a lightweight mode and a full-spec mode using EARS, a format for writing precise software requirements.

In plain words
What is it for?
Use it to create plans and task files in docs/dev/plans/ for features, bug fixes, or larger system changes.
Why use it?
It breaks vague or large requirements into work that developers can implement and check. It expects an existing project context file created by dev-context.

Skill for Claude CodeCodex

974 25d ago A scan 148 tokens original MIT
View the source file classmethod/tsumiki
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/classmethod/tsumiki/dev-plan
Any agent
npx skills add classmethod/tsumiki --skill dev-plan
Clone the repo
git clone --depth 1 https://github.com/classmethod/tsumiki

Made for: Claude Code, Codex.

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,151 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 $0.00148 $0.05151
Opus 5 $0.00074 $0.02576
Sonnet 5 $0.00030 $0.01030
Haiku 4.5 $0.00015 $0.00515

Measured 2d ago against content hash 21dcab93ed53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-plan 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.

skills/dev-plan/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Plan

ユーザーの要件を分析し、インターフェースファーストの設計とテスト可能なタスクに分解する。Plan名で名前空間を分離し、複数要件の並行開発をサポートする。出力は docs/dev/plans/<plan-name>/ に保存される。

前提知識

dev-*スキルフロー内の位置

dev-context → [dev-plan] → dev-impl → dev-verify

前提条件

  • docs/dev/context.md が存在すること（dev-contextで生成済み）
  • context.md がない場合、先に /dev-context の実行を案内する

依存スキル

  • task-breakdown: Full-spec モードの Phase 3（タスク分解）で、その4フェーズ分解手順を embedded 規約に準じてインライン適用する（詳細は Phase 3「Full-spec モード」参照）。

引数フォーマット

/dev-plan <plan-name> "<要件の説明>"
/dev-plan <plan-name> <PRDファイルパス>
  • plan-name: 英数字とハイフンのみ（例: auth, payment-integration, user-profile）
    • 日本語が含まれる場合は自動変換する（Phase 0.5 参照）
  • 要件の説明: 自然言語での機能要件
  • PRDファイルパス: PRD ドキュメントのファイルパス（.md 等）。ファイル内容を要件として読み込む

実行モード

モード 説明 出力
Lightweight 素早い要件明確化→設計→タスク分解 plan.md + tasks/
Full-spec EARS要件定義→ユーザーストーリー→受入基準→設計→タスク分解 requirements.md + user-stories.md + acceptance-criteria.md + plan.md + tasks/

ワークフロー

Phase 0: モード選択

AskUserQuestion で実行モードを選択する:

  • Lightweight（推奨: 小さな機能追加・バグ修正）: 素早く要件を明確化し、設計→タスク分解まで進む
  • Full-spec（推奨: 新規システム・複雑な要件）: EARS要件定義→ユーザーストーリー→受入基準を作成した上で、設計→タスク分解に進む

選択されたモードに応じて以降の Phase の振る舞いが変わる。

Phase 0.5: plan-name の正規化

plan-name に日本語（非ASCII文字）が含まれる場合、以下のルールで英数字ケバブケースに自動変換する:

  1. 日本語の要件名を簡潔な英語に翻訳する
  2. ケバブケース（kebab-case）に変換する
  3. 最大50文字程度に収める
  4. 変換例:
    • "ユーザー認証システム" → user-auth-system
    • "データエクスポート機能" → data-export
    • "パスワードリセット" → password-reset
    • "お気に入り管理" → favorite-management
    • "検索フィルター追加" → search-filter
  5. 変換後のplan-nameをユーザーに提示し、確認を取ってから続行する

plan-name が既に英数字とハイフンのみの場合はこのフェーズをスキップする。

Phase 1: 要件明確化

  1. 要件入力の判定: 第2引数がファイルパスかテキストかを判定する
    • ファイルパスの場合（パスに / を含む、または .md 等の拡張子で終わる）→ Read ツールでファイルを読み込み、内容を要件として使用する
      • PRDファイルが 200行を超える 場合:
        1. 最初の200行を Read で読み込む
        2. 残りは Explore サブエージェント（model: haiku）で要約を取得する
        3. メインコンテキストには 先頭200行 + 要約（50行以内） のみ保持する
    • ファイルが存在しない場合 → エラーメッセージを表示して終了する
    • テキストの場合 → 従来通りテキストを要件として使用する
  2. docs/dev/context.md を読み込み、プロジェクトコンテキストを把握する
  3. ユーザーの要件（テキストまたはPRDファイル内容）を分析し、不明確な点を特定する
  4. AskUserQuestion で曖昧さを段階的に解消する（最大2-3ラウンド）

Read the full file on GitHub · 278 lines

Files

What ships with it

4 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 · 278 lines · 148 tokens per session scan A 21dcab93ed53

Subscribe to this mod's changes

dev-plan is a skill published in the GitHub repository classmethod/tsumiki (974 stars, last pushed 25d ago), licensed MIT. It adds 148 tokens to every session and 5,151 once invoked, about $0.0007 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.

DebuggingDocumentsWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens