book-writer CLAUDE.md

book-writer CLAUDE.md is an instructions file for Claude Code from tobyilee/book-writer. It costs 6,042 tokens per session, scanned A, original, MIT.

A repository instruction document for an automated book-writing project that researches a topic, plans and reviews chapters, writes them, and builds an EPUB ebook. It also describes genre-specific writing profiles and output files.

In plain words
What is it for?
Use it to create or revise technical books, practical guides, essays, or narrative ebooks, including their EPUB and reader-facing Markdown description.
Why use it?
It gives the writing workflow consistent rules for research, style, author details, revisions, and ebook production.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

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 instructions/tobyilee/book-writer/claude-md
Clone the repo
git clone --depth 1 https://github.com/tobyilee/book-writer

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 book-writer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tobyilee/book-writer/claude-md.svg)](https://agentmods.dev/instructions/tobyilee/book-writer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tobyilee/book-writer/claude-md"><img src="https://agentmods.dev/badge/instructions/tobyilee/book-writer/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,042 This file is loaded in full into every session.
When invoked 6,042 The same file — it is already loaded in full.
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 5.1 $0.06042 $0.06042
Opus 5 $0.03021 $0.03021
Sonnet 5 $0.01208 $0.01208
Haiku 4.5 $0.00604 $0.00604

Measured 6d ago against content hash a7d215899203, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

book-writer 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 6d 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Book Writer Project

주제·주요 내용·대상 독자가 주어지면 완성된 EPUB을 산출하는 자동화 하네스가 구축되어 있다.

하네스: 책 저술 자동화

목표: 주제가 주어지면 리서치 → 저술 계획 → 계획 리뷰 → 챕터 저술(Toby 스타일) → EPUB 빌드까지 자동 수행한다. 저자명은 기본값 Toby-AI이며, 사용자가 프롬프트에 저자: {이름} 한 줄을 넣으면 그 값이 매니페스트·표지·EPUB 메타까지 그대로 전파된다.

트리거: 책/전자책/EPUB 저술 관련 작업 요청 시 book-writing-orchestrator 스킬을 사용하라. 특정 Phase만 재실행하거나 챕터 수정 요청도 동일 스킬이 처리한다. 단순 질문(예: "책 저술이 뭐야?")은 직접 응답 가능.

스타일 가이드 (장르 프로필): 하네스 v1.3.0부터 문체는 단일 가이드가 아니라 장르별 프로필(profiles/{genre}/)로 관리된다. 오케스트레이터가 Phase 0에서 장르(tech-book/narrative/practical/essay, 기본 tech-book)를 감지·확인하면, 그 프로필의 voice.md·scaffolds.md·style-checklist.md가 저술·검수의 제약 조건이 된다. 챕터 저술가와 스타일 가디언은 활성 프로필을 준수한다. 프로필 목록·선택 규칙은 profiles/_registry.md. 루트 toby-book-writing-style.mdtech-book 프로필의 뿌리이자 하위호환 기준 문서로 유지된다. 확장 후속(장르별 fact-checker·구조화 EPUB·소설 연속성 추적)은 docs/harness-roadmap.md 참조.

산출 경로:

  • 중간 산출물: {book-slug}/
  • 최종 산출물(프로젝트 루트, 같은 폴더에 짝으로 산출):
    • {책-제목}-v{version}.epub — 본문 EPUB
    • {책-제목}-v{version}.md — 외부 독자용 책 소개 markdown (logline·대상 독자·차례·저자 소개)

브랜치 운영 패턴: 하네스 자체(에이전트·스킬·CLAUDE.md·README)는 main 브랜치에서 관리하고, 각 책은 자기 브랜치(예: rust-for-java-developer, french-cooking, worktree-sf)에서 산출한다. 새 책을 시작할 때는 main에서 새 브랜치를 따고, 거기서 오케스트레이터를 돌린다. 이렇게 하면 하네스 변경과 책 산출물이 섞이지 않는다.

반드시 현재 main에서 분기하라. 책 worktree는 분기 시점의 하네스 스펙(에이전트·스킬·프로필)을 자동 로드한다 — 오래된 브랜치나 worktree(예: .claude/worktrees/team-five/...의 스냅샷)에서 분기하면 자동 로드되는 스펙이 정전(canonical)과 어긋나 구버전 동작으로 산출된다. 새 책은 항상 최신 main에서 따서 시작한다.

학습 루프 (두 개): 하네스에는 방향이 다른 두 학습 루프가 있다 — 하네스 자신이 책 산출 교훈을 누적하는 하네스 학습 루프(book-lessons.md, v1.8.0)와, 운영자(인간)의 판단력이 완전 위임으로 마모되지 않게 상호작용 기본값(선판단 후공개·설계 근거 동봉)·로그 기반 직접 검수 표적·위임 다이얼(delegation_mode: production|learning)을 설계한 운영자 학습 루프(v1.9.0). 운영자 터치포인트는 전부 자문 전용·비블로킹이며 production 기본값은 기존 동작과 동일하다. 정전 스펙은 docs/learning-loop.md.

하네스 버전: 프로젝트 루트의 VERSION 파일이 단일 출처. 현재 v1.11.0. 책 매니페스트의 version(책의 판본)과 다른 개념이다 — 하네스는 도구의 진화, 책 매니페스트는 각 책의 개정을 추적한다. 매니페스트의 harness_version 필드를 통해 산출된 책의 콜로폰에도 노출된다.

Read the full file on GitHub · 52 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. 6d ago First seen · 52 lines · 6,042 tokens per session scan A a7d215899203

Subscribe to this mod's changes

book-writer CLAUDE.md is an instructions file published in the GitHub repository tobyilee/book-writer (81 stars, last pushed 19d ago), licensed MIT. It adds 6,042 tokens to every session, about $0.0302 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.

Related

Other instructions, from other repositories

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

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 · 5,182 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