agentmods.dev

sdd-starter: Instructions file for Claude Code

CLAUDE.md

sdd-starter CLAUDE.md is an instructions file for Claude Code from KazukiShinomiya/sdd-starter. It costs 1,530 tokens per session, scanned A, original, Unlicense.

Project instructions for Claude Code in a Japanese specification-driven development template. They explain shared project context, the required workflow, branch and pull-request rules, and checks that must work on both Unix-like systems and Windows.

In plain words
What is it for?
Use them when Claude Code works in this repository, especially while planning, specifying, analyzing, implementing, or checking a feature.
Why use it?
They keep agents from duplicating the project's source instructions, skipping required design stages, or making structural changes without verification.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is KazukiShinomiya/sdd-starter's own configuration. It tells Claude Code how to work on sdd-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sdd-starter configures →

not rated 1repo 1mo ago A scan 1,530 tokens original Unlicense
View source ↗ KazukiShinomiya/sdd-starter
Reuse

Borrowing it

Nothing to install: this file belongs to KazukiShinomiya/sdd-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/KazukiShinomiya/sdd-starter/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/KazukiShinomiya/sdd-starter

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 sdd-starter CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kazukishinomiya/sdd-starter/claude-md/github.svg)](https://agentmods.dev/instructions/kazukishinomiya/sdd-starter/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kazukishinomiya/sdd-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/kazukishinomiya/sdd-starter/claude-md/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.

agentmods 80×15 button for sdd-starter CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kazukishinomiya/sdd-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/kazukishinomiya/sdd-starter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,530 This file is loaded in full into every session.
When invoked 1,530 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01530 $0.01530
Opus 5 $0.00765 $0.00765
Sonnet 5 $0.00306 $0.00306
Haiku 4.5 $0.00153 $0.00153

Measured 10d ago against content hash f7a9afe2aa22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sdd-starter CLAUDE.md 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 10d 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.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Claude Code がこのリポジトリで作業するときの文脈。これは仕様駆動開発（SDD）テンプレートだ。 このファイルは Claude 固有の運用指針 に絞る。エージェント非依存の文脈は AGENTS.md、 ロジックの本体は prompts/*.md にある（下記）。

このテンプレートを使って自分のプロダクトを作る場合は、このファイルを差し替えてよい。 ここに書くのは「SDD テンプレートとして作業する」ための指針であって、下流プロダクトの ルールではない。移行の全体手順は docs/adopting.md を参照。

共有文脈（全エージェント共通）

@AGENTS.md

AGENTS.md が技術スタックと最近の変更を蓄積する永続文脈だ（AUTO:BEGIN〜AUTO:END は /plan が機械更新する）。Cursor / Copilot / Gemini も同じ AGENTS.md を読む。

このプロジェクトの核（変更時に守る）

  • 真実の源は prompts/*.md。各エージェントの入口（.claude/commands/ 等）は、対応する prompt を読むだけの薄いラッパだ。ロジックを二重に書かない。
  • ワークフロー: constitution → specify →〔clarify〕→ plan → tasks →〔analyze〕→ implement。各段階は検証可能な Markdown 成果物を残し、次段階の入力になる。人間に断りなく 段階を飛ばして先へ進めない。
  • 1機能 = 1ブランチ = 1 PR。scripts/new-feature.{sh,ps1} が次の連番で specs/NNN-*/ を作り、 機能ブランチを切る。
  • 品質ゲートは両肺主義。検査ロジックは bash と PowerShell に同じものを刻み、CI で両 OS を回す。 構造に触れる変更の前後で bash scripts/check.sh（Windows は .\scripts\check.ps1）を通す。

Claude 固有の運用指針

  • サブエージェント委譲: 重い /analyze・/implement で対象が大きいときは、コンテキスト保全と 独立検証のためサブエージェントに委譲してよい。ただし spec.md / plan.md / tasks.md （真実の源）への書き込みは親が一元管理する。サブエージェントには読み取り・分析・限定的な実装を 任せ、成果物への最終統合は親が担う。これにより複数の書き手が真実の源を奪い合う事態を防ぐ。
  • prompts/ はエージェント非依存に保つ。サブエージェント等の Claude 固有概念を prompts/*.md に 書かない。それらはこの CLAUDE.md に留め、prompts/ はどのエージェントでも同じ結果を出す 真実の源であり続ける。
  • 構造変更の自動検査（フック）: .claude/settings.json の PostToolUse フックが、あらゆる Write / Edit の直後に check.sh を自動実行する（${CLAUDE_PROJECT_DIR} 起動・セッションの CWD に依らず発火する。発火条件でのパス絞り込みは、その照合が CWD 相対で静かな不発火を生む ため廃止——specs/005）。検査は読み取り専用・実測 ~1秒。検査が NG なら その内容がエージェントに即時フィードバックされるので、その場で直してから先へ進むこと。
    • 品質ゲートの本体はあくまで check.{sh,ps1} と CI 側。フックは気づきを前倒しする便利装置で、 Cursor 等フックの無い環境でも手動実行で同じ結論に至る（この退路を壊さない）。
    • 検査は読み取り専用。段階遷移（specify → plan 等）の自動起動はしない——それは唯一の禁則だ。
    • 前提は bash（Windows は Claude Code 標準の Git Bash）。個人環境でこの自動化だけ切りたければ、 .claude/settings.local.json（gitignore 済み）に "disableAllHooks": true を書く。
  • 限定 skill 実験（specs/007）: .claude/skills/ に status / analyze の2つだけを 同名 skill として展開している。同名 skill はコマンドより優先されるため、Claude Code では /status・/analyze の実体が skill 側になり（同じ prompts/*.md を読む薄いラッパゆえ 結論は不変）、文脈上有用ならモデル判断の自発起動が加わる。境界は三層: ①自発起動が許されるのはこの2コマンドの実行まで（結果を根拠に他の SDD 段階を起動しない） ②analyze のレポート保存は保存前にユーザーの承認を得る（読み取りは skill の自由・ 書き込みは人間の承認）③他9コマンドは skill 化しない——全面 skill 化は自律起動が SDD の教育的価値と衝突するため見送り済み（2026-06-05 の決着）。戻し方: .claude/skills/ を削除するだけで完全復元。skills は品質ゲートの入口整合検査（11コマンド全対応前提）の 対象外の意図的サブセット。

Read the full file on GitHub · 59 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. 10d ago First seen · 59 lines · 1,530 tokens per session scan A f7a9afe2aa22

Subscribe to this mod's changes

sdd-starter CLAUDE.md is an instructions file published in the GitHub repository KazukiShinomiya/sdd-starter (1 stars, last pushed 1mo ago), licensed Unlicense. It adds 1,530 tokens to every session, about $0.0076 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.

Claude Codeai-agentscursorgemini-cligithub-copilotjapanese
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens