book-writer: Skill for Claude Code

.claude/skills/book-writing-orchestrator/SKILL.md

book-writing-orchestrator is a skill for Claude Code from tobyilee/book-writer. It costs 0 tokens per session (4,343 once invoked), scanned A, original, MIT.

A coordinator for writing a complete book, from choosing and researching a topic through planning, drafting, review, cover creation, and EPUB production.

In plain words
What is it for?
Use it when you have a topic, key content, and target readers and want a finished book workflow, including intermediate files, a cover image, and an EPUB.
Why use it?
It removes the need to manage the many stages and specialist roles of book production yourself.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is tobyilee/book-writer's own configuration. It tells Claude Code how to work on book-writer 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 book-writer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tobyilee/book-writer. 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/tobyilee/book-writer/main/.claude/skills/book-writing-orchestrator/SKILL.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-writing-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/tobyilee/book-writer/book-writing-orchestrator/github.svg)](https://agentmods.dev/skills/tobyilee/book-writer/book-writing-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/tobyilee/book-writer/book-writing-orchestrator"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/book-writing-orchestrator/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 book-writing-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/tobyilee/book-writer/book-writing-orchestrator"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/book-writing-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,343 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.04343
Opus 5.5 $0.00000 $0.01737
Sonnet 5.5 $0.00000 $0.00869
Haiku 4.5 $0.00000 $0.00434

Measured 1mo ago against content hash 0eceaceaccb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

book-writing-orchestrator 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/skills/book-writing-orchestrator/SKILL.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.

Book Writing Orchestrator

주제·주요 내용·대상 독자를 받아 완성된 EPUB을 산출한다. 각 Phase에서 전문 에이전트를 호출하고, 중간 산출물을 {slug}/에 쌓은 뒤 최종 EPUB과 책 소개 markdown을 프로젝트 루트에 만든다.

흐름 한눈에

Phase 누가 산출물
0. 컨텍스트 오케스트레이터 장르·저자·라이선스·슬러그·위임 모드 확정
1. 리서치 리서처 2~3명 병렬 → research-lead(합성) research/*.md, 01_reference.md
2. 계획 book-planner 02_plan.md (+ narrative면 story_bible.md 시드)
3. 계획 승인 사용자 승인된 02_plan.md
4. 저술 chapter-writer 최대 4명 병렬 → 묶음별 fact-checker/continuity-keeper → editor chapters/*, 04_manuscript.md, book_manifest.json, (narrative) pacing_report.md
4.5. 수락 게이트 manuscript-reviewer (신선 컨텍스트) 05_acceptance.md
5. 표지 + EPUB cover-designer(백그라운드) + epub-builder {책-제목}-v{version}.epub·.md

독립 검수는 두 곳에만 둔다 — 챕터 묶음마다 한 번의 사실/연속성 패스, 그리고 통권 수락 게이트 한 번. 저술가는 활성 프로필의 체크리스트를 자기 품질 기준으로 삼아 쓰므로 별도의 스타일 왕복 검수는 기본 흐름에 없다(요청 시 style-guardian을 쓴다).

서브에이전트 운용

  • 에이전트는 Agent 도구로 호출하고, 서로 독립인 호출(리서처들, 저술가들)은 한 메시지에 모아 병렬로 띄운다. 팀 도구(TeamCreate·SendMessage)에 의존하지 않는다 — 모든 조율은 {slug}/의 파일과 반환값으로 한다.
  • 첫 브리프에 필요한 것을 다 담는다: genre, 슬러그, 담당 범위(챕터 번호 등), 읽을 파일 경로, 쓸 파일 경로, 저자·라이선스처럼 이 Phase에 필요한 사용자 지정값. 파일 내용을 프롬프트에 붙여넣지 말고 경로를 준다.
  • 각 에이전트에게 반환값은 짧게 요청한다 — 쓴 파일 경로, 미해소 항목, 사용자 판단이 필요한 것. 반환된 결과를 오케스트레이터가 다시 검증하거나 다시 쓰지 않는다.
  • 모델은 지정하지 않는다. 모든 에이전트가 현재 세션의 모델 설정을 그대로 상속한다 (frontmatter에도 model을 두지 않는다).
  • 에이전트가 중단되면 이미 쓴 파일(로그는 챕터마다 즉시 append된다)을 확인하고, 남은 범위만 담아 다시 호출한다.

Phase 0: 컨텍스트 확인

  1. 사용자 입력에서 주제·주요 내용·대상 독자를 뽑는다. 하나라도 불명확하면 AskUserQuestion으로 짧게 묻는다. 저자: {이름}이 있으면 그 값, 없으면 Toby-AI. 라이선스: {값}이 있으면 그 값, 없으면 매니페스트 license를 비워 빌드 스크립트 기본값(CC BY-NC-SA 4.0)을 쓴다.
  2. 장르를 정한다. 장르: {값}이 있으면 그대로 쓴다. 없으면 profiles/_registry.md의 감지 규칙으로 추정하고, 신호가 분명하면 알리고 진행하며, 애매하면 AskUserQuestion으로 추정값을 첫 옵션으로 제시해 확인받는다.
  3. 위임 모드를 정한다. 모드: 학습이나 "이 주제를 공부하려고" 같은 명확한 학습 신호가 있으면 learning, 없으면 묻지 않고 production. 어차피 질문할 일이 있으면 거기에 함께 묻는다 (docs/learning-loop.md).
  4. 같은 genre의 교훈이 book-lessons.md(없으면 .omc/book-lessons.md)에 있으면 최근 몇 건을 읽어 planner·writer 브리프에 참고 메모로 넣는다. 파일이 없으면 건너뛴다.
  5. 제목 후보와 슬러그를 만든다 (예: AI 시대의 개발자 철학 → ai-developer-philosophy). {slug}/가 없으면 새 실행, 있고 부분 수정 요청이면 재실행 매트릭스를 따르고, 있는데 완전히 새 입력이면 기존 폴더를 {slug}_prev-{timestamp}/로 옮긴 뒤 새로 시작한다. 재실행에서는 book_manifest.json의 genre·delegation_mode를 그대로 쓴다.

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. 1mo ago Changed · -85 lines 0eceaceaccb1
  2. 2mo ago First seen · 215 lines · 0 tokens per session scan A c3774b4c8f88

Subscribe to this mod's changes

book-writing-orchestrator is a skill published in the GitHub repository tobyilee/book-writer (85 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,343 tokens. 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

book-writing-orchestrator compared with skills from other repositories

book-writing-orchestrator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
book-writing-orchestratortobyilee/book-writerSkill853d agoMITA0Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code