book-writer: Skill for Claude Code

.claude/skills/book-planning/SKILL.md

book-planning is a skill for Claude Code from tobyilee/book-writer. It costs 80 tokens per session (1,046 once invoked), scanned A, original, MIT.

A book-outline workflow that turns research into a title, book structure, chapter sequence, and description of what each chapter covers.

In plain words
What is it for?
Use it to plan technical books, practical guides, essays, or narrative works, including the reader's starting point, expected outcome, chapter questions, content, and approximate length.
Why use it?
It helps prevent missing topics, weak chapter order, uneven coverage, and a mismatch between the book and its intended readers.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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-planning/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-planning

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tobyilee/book-writer/book-planning"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/book-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 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 $0.00080 $0.01046
Opus 5.5 $0.00032 $0.00418
Sonnet 5.5 $0.00016 $0.00209
Haiku 4.5 $0.00008 $0.00105

Measured 1mo ago against content hash 4b210cd5793e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

book-planning 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-planning/SKILL.md · 74 lines

What it actually says

Book Planning

좋은 계획은 "독자가 어떤 여정을 거쳐 무엇을 얻는가"를 먼저 정하고, 거기서 역산해 챕터를 배치한다. 오케스트레이터가 확정한 genre(기본 tech-book)의 profiles/{genre}/scaffolds.md를 읽고 그 장르의 단위로 짠다.

독자 여정

진입 상태(이 독자는 왜 이 책을 집었나, 무엇을 알고 무엇이 고민인가)에서 출구 상태(다 읽고 나면 무엇을 할 수 있고 무엇이 바뀌었나)를 정한다. 출구는 장르마다 다르다 — tech-book과 practical은 "할 수 있다", narrative는 "느낀다", essay는 "바뀐다". 그 사이에 각성(놓친 것을 깨닫는 지점), 배움, 적용, 종합이 어디서 일어나는지 배치한다.

챕터 배치

  • 5~10장을 기본으로 하고 주제 폭에 맞춰 조정한다.
  • 첫 장은 왜 이 주제·이 책인지, 중반은 무엇과 어떻게를 교차하고, 종반은 부분 지식을 묶고, 마지막 장은 덮은 뒤의 다음 걸음을 남긴다 (narrative는 서사 아크가 우선).
  • 레퍼런스의 주요 자료가 어딘가에 배치되고, 인접 챕터가 겹치지 않고, 난이도가 갑자기 뛰지 않고, 챕터 예상 분량의 합이 목표 분량에 맞아야 한다.

통권 변주 배정

각 챕터에 셋을 배정한다 (scaffolds의 메뉴에서):

  • 오프닝 기법 — 인접 챕터와 다르게. tech-book에서 '상황 가정'은 전체의 1/3 이하.
  • 클로징 기법 — 전 챕터가 서로 다르게. 마지막 장은 여정을 회수하는 닫는 매듭.
  • 스캐폴드 유형 — tech-book: 개념 도입형·문제-해결형·사례 분석형·비교 대조형·종합 정리형. 다른 장르는 해당 프로필의 유형.

출력: {slug}/02_plan.md

# {주제} 저술 계획

## 제목 후보
1. **{후보1}** — 톤: {...}, 포지셔닝: {...}
2. **{후보2}** — ...
3. **{후보3}** — ...
**추천:** {후보N} (이유)

## 책 특성
- 장르: {...}
- 분량: {전체 글자 수}
- 난이도: {초급 / 중급 / 고급}
- 독자 여정: {진입 상태} → {출구 상태}

## 내러티브 아크
{챕터 흐름과 이 순서인 이유를 문단으로}

## 설계 근거
- **채택한 구조:** {핵심 이유 2~3개}
- **기각한 대안 1:** {한 줄 요약} — 기각 사유: {...}
- **기각한 대안 2:** {한 줄 요약} — 기각 사유: {...}

## 용어 표기
- {핵심 용어}: {이 책에서 쓸 표기}

## 챕터 목록

### 1장. {제목}
- **핵심 질문:** {...}
- **주요 내용:** {3~5개 불릿}
- **독자가 얻는 것:** {...}
- **오프닝 기법:** {...}
- **클로징 기법:** {...}
- **스캐폴드 유형:** {...}
- **예상 분량:** {글자 수}

### 2장. ...

"용어 표기"는 병렬로 쓰는 저술가들이 같은 표기를 쓰게 하는 기준이다. 핵심 용어 5~15개면 충분하다.

리뷰 피드백 반영

03_review_log.md나 사용자 피드백이 오면 Critical은 반영하고, Should는 반영하거나 근거를 적어 기각하고, Nice는 선택한다. 변경 요약은 02_plan.md 끝의 "개정 이력"에 남긴다.

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 · -12 lines 4b210cd5793e
  2. 2mo ago First seen · 86 lines · 80 tokens per session scan A 1a51dc019370

Subscribe to this mod's changes

book-planning is a skill published in the GitHub repository tobyilee/book-writer (85 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 1,046 once invoked, about $0.0003 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 2026-08-30.

Related

book-planning compared with skills from other repositories

book-planning next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
book-planningtobyilee/book-writerSkill853d agoMITA80Claude 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