sdnd-template: Instructions file for Claude Code

CLAUDE.md

sdnd-template CLAUDE.md is an instructions file for Claude Code from piperendervt-glitch/sdnd-template. It costs 874 tokens per session, scanned A, original, MIT.

A project instruction file for a specification-driven novel project. It defines which story documents to read, how canon and character state are organised, and the rules for Git changes.

In plain words
What is it for?
Use it to guide episode writing, specification updates, canon management, reference-file checks, and safe Git operations in a structured fiction project.
Why use it?
It gives coding agents shared project context so they can preserve story continuity and follow the project's review and merge rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is piperendervt-glitch/sdnd-template's own configuration. It tells Claude Code how to work on sdnd-template 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 sdnd-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to piperendervt-glitch/sdnd-template. 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/piperendervt-glitch/sdnd-template/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/piperendervt-glitch/sdnd-template

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 sdnd-template CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/piperendervt-glitch/sdnd-template/claude-md/github.svg)](https://agentmods.dev/instructions/piperendervt-glitch/sdnd-template/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/piperendervt-glitch/sdnd-template/claude-md"><img src="https://agentmods.dev/badge/instructions/piperendervt-glitch/sdnd-template/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 sdnd-template CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/piperendervt-glitch/sdnd-template/claude-md"><img src="https://agentmods.dev/badge/instructions/piperendervt-glitch/sdnd-template/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 874 This file is loaded in full into every session.
When invoked 874 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 $0.00874 $0.00874
Opus 5.5 $0.00350 $0.00350
Sonnet 5.5 $0.00175 $0.00175
Haiku 4.5 $0.00087 $0.00087

Measured 1mo ago against content hash 4f7cb42bfee6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdnd-template 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 1mo 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 · 70 lines

What it actually says

{プロジェクト名}

概要

このプロジェクトは SDND(Spec-Driven Novel Development)フレームワークを使った長編小説制作プロジェクトです。 仕様駆動で物語の整合性を保ちながら、エピソード単位で執筆・検査・正史登録を行います。

現在のフェーズ

{現在の執筆フェーズ。例: Arc 1 執筆中(EP-001〜)}

参照すべきドキュメント

常時読み込み(TIER 1)

  • specs/core/invariants.md — 不変ルール(INV-*)
  • specs/core/characters_state.md — キャラ現在状態
  • canon/quick_ref.md — Canon最新状態スナップショット

エピソード実行時(TIER 2)

  • canon/active/*.md — 直近N話のCANONエントリ
  • meta/open_loops.md — オープンループ一覧

参照時のみ(TIER 3)

  • specs/reference/world.md — 世界設定
  • specs/reference/system.md — {コアシステム}体系
  • specs/reference/characters_detail.md — キャラ詳細設定
  • canon/archive/*.md — 過去CANONエントリ

ガイド・ポリシー

  • docs/ARCHITECTURE.md — プロジェクト構成ガイド
  • specs/_index.md — スペック読み込み階層ガイド
  • canon/README.md — Canon運用ルール
  • meta/phase_plan.md — フェーズ計画

テンプレート

  • canon/active/CANON-TEMPLATE.md — CANONエントリテンプレート

ツール

  • tools/ — 自動化スクリプト

設計方針

  • canon は3層分離構造(quick_ref + active + archive)
  • Specs は TIER 1(必須)/ TIER 2(実行時)/ TIER 3(参照時)に階層化
  • open_loops.md は canon 確定のブロッキングゲートで同期を強制
  • active ウィンドウのサイズは sdnd-config.yaml の canon.active_window で設定

Git 運用ルール

  • commit とブランチ操作は自動で実行してよい
  • main/master への merge は、実行前に必ずユーザーに確認を求めること
  • commit メッセージは [story], [spec], [canon], [qa], [chore] のprefixを付けること

サブエージェント運用ルール

本プロジェクトでは3つのサブエージェントを使い分ける。

エージェント 役割 起動タイミング
writer EP本文と canon-proposal の執筆 「EP-NNN を書いて」
qa QAレポートの作成 「EP-NNN をQAして」
editor Canon登録・仕様更新 「Canon登録して」「仕様を修正して」

ファイル変更権限

  • writer: story/ のみ書き込み可。specs/ は読み取りのみ
  • qa: qa/reports/ のみ書き込み可。story/ specs/ は読み取りのみ
  • editor: specs/ meta/ canon/ のみ書き込み可

ワークフロー

  1. メインセッション(PM)が writer を呼び出し → EP本文が生成される
  2. メインセッション(PM)が qa を呼び出し → QAレポートが生成される
  3. QA PASS なら editor を呼び出し → Canon登録・仕様更新
  4. QA に指摘があれば writer を再度呼び出し → 修正
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. 1mo ago First seen · 70 lines · 874 tokens per session scan A 4f7cb42bfee6

Subscribe to this mod's changes

sdnd-template CLAUDE.md is an instructions file published in the GitHub repository piperendervt-glitch/sdnd-template (5 stars, last pushed 8mo ago), licensed MIT. It adds 874 tokens to every session, about $0.0035 per session on Opus 5.5. 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 2026-10-02.

Related

sdnd-template CLAUDE.md compared with instructions from other repositories

sdnd-template CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sdnd-template CLAUDE.mdpiperendervt-glitch/sdnd-templateInstructions file58mo agoMITA874Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode