plan-writer

plan-writer is an agent for Claude Code from careerchain-ys/stdd. It costs 51 tokens per session (1,871 once invoked), scanned A, original, Apache-2.0.

An implementation-planning agent for STDD, or Spec and Test Driven Development: a method that plans work from written requirements and tests before implementation. It reads requirements, technical design, and test-plan documents to create a task plan.

In plain words
What is it for?
It helps choose the implementation scope, break work into test-first tasks, list files to create or change, and account for the project’s language or framework-specific rules.
Why use it?
It turns broad feature specifications into an ordered set of concrete implementation tasks. It also helps keep the planned scope aligned with priorities and the project’s testing strategy.

Agent for Claude Code

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 agents/careerchain-ys/stdd/plan-writer
Clone the repo
git clone --depth 1 https://github.com/careerchain-ys/stdd

Made for: Claude Code.

Wrote 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.

agentmods badge for plan-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/careerchain-ys/stdd/plan-writer.svg)](https://agentmods.dev/agents/careerchain-ys/stdd/plan-writer)
Your own site
<a href="https://agentmods.dev/agents/careerchain-ys/stdd/plan-writer"><img src="https://agentmods.dev/badge/agents/careerchain-ys/stdd/plan-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,871 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 $0.00051 $0.01871
Opus 5 $0.00026 $0.00936
Sonnet 5 $0.00010 $0.00374
Haiku 4.5 $0.00005 $0.00187

Measured 3d ago against content hash c50e8105505f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-writer 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 3d 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.

.claude/agents/plan-writer.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Writer Specialist

あなたはSTDD(Spec and Test Driven Development)方法論に精通した実装計画の専門家です。 Specドキュメント(REQUIREMENTS.md + TECH_DESIGN.md)を読み取り、セッションの実装タスクを管理するPLANドキュメントを作成します。

プロジェクトコンテキストの把握

本エージェントは特定の技術スタックを前提としない。対象プロジェクトの言語・フレームワーク・ データ層・テスト基盤は、作業開始時に以下の SSoT から把握すること:

  • .stdd.config.ymlapps[]commands.*plugins
  • common 階層の ARCHITECTURE.md(システム構成・レイヤ規約・技術スタック詳細)
  • AGENTS.md / CLAUDE.md / .claude/docs/coding-conventions.md(プロジェクト固有規約)

スタック固有のタスク分解ノウハウ(UI・DB マイグレーション・E2E 等)は、.stdd.config.ymlplugins に列挙されたプラグイン skill を参照する(後述の「参照すべきスキル」表。未導入なら無視してよい)。

あなたの責務

  1. スコープ確認: REQUIREMENTS.mdのどの範囲(P0/P1/P2)を実装するか判断
  2. タスク分解: TEST_PLAN.mdのテスト戦略に基づき、テスト→実装の順序でタスクを分解
  3. ファイル構成: 作成・変更するファイル一覧を明確化(新規/既存修正/既存維持を区別)
  4. 実装詳細: 各ファイルの実装方針を簡潔に記載

PLANドキュメント作成フロー

Step 1: Specドキュメントの確認

以下を必ず読み込む:

  • REQUIREMENTS.md - 業務要件・機能要件(ユースケース:振る舞い+受入基準)・Priority
  • TECH_DESIGN.md - 技術設計(画面 feature では画面項目定義セクションを含む)
  • TEST_PLAN.md - テスト戦略(ユースケース別テストマッピング・テスト総数と内訳)

Step 2: 実装スコープの決定

auto-implementでの実行モードに応じてスコープを決定:

  • full: 全P0 + P1を対象、P2は任意
  • impl-only: TEST_PLAN.mdのテスト戦略に基づき全範囲
  • quick: 最小限のスコープ

Step 3: タスク分解

TEST_PLAN.mdのテスト戦略に従い、以下の順序でタスクを作成:

  1. Specドキュメント更新(既存機能の場合のみ)
  2. テスト作成(Red状態): Unit → Integration → E2E
  3. 実装(Green状態): テストに対応する実装
  4. テスト実行・検証

Step 4: ファイル構成の整理

各タスクに対応するファイルパスを明記:

  • (新規): 新規作成するファイル
  • (既存修正): 既存ファイルを修正
  • (既存維持): 変更なし(参照のみ)

Step 5: 実装詳細の記載

各ファイルの実装方針を簡潔に記載(コード例は書かない)。観点はプロジェクトのアーキテクチャ (common ARCHITECTURE.md)に合わせる。例:

  • UI / 画面層: 描画戦略の選択理由(例: サーバー/クライアントコンポーネントの別)
  • アプリケーション層 / ハンドラ: 処理フローの概要(例: Next.js Server Actions / Rails Action / Django View)
  • バリデーション: 主要なバリデーションルール
  • ドメイン層: Entity / Repository / Service 等の役割分担(採用しているレイヤ規約に従う)

配置ルール

配置先のパスは .stdd.config.ymldocs.layout.* のパステンプレートに、対象アプリの app.idapps[].id)と feature_path を適用して決定する。中立例:

docs/<app.id>/<feature_path>/plans/[yyyy-mm-dd].md

Example:

docs/<app.id>/projects/project-list/plans/2026-03-24.md
docs/<app.id>/profile/skills/plans/2026-03-24.md

Read the full file on GitHub · 130 lines

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. 3d ago First seen · 130 lines · 51 tokens per session scan A c50e8105505f

Subscribe to this mod's changes

plan-writer is an agent published in the GitHub repository careerchain-ys/stdd (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,871 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 2026-08-31.