book-writer: Agent for Claude Code

.claude/agents/chapter-writer.md

chapter-writer is an agent for Claude Code from tobyilee/book-writer. It costs 47 tokens per session (948 once invoked), scanned A, original, MIT.

A writing agent that drafts one book chapter from a plan and related research. It saves a draft, requests a style review, and then saves a revised final version.

In plain words
What is it for?
Use it to produce chapter drafts from a book plan, incorporate reference material, and prepare reviewed chapter files for an editor.
Why use it?
It removes the need to coordinate planning, research, drafting, and style feedback manually for each chapter. It also checks that the writing follows the selected genre rather than assuming every book uses the same tone.

Agent 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/agents/chapter-writer.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 chapter-writer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/tobyilee/book-writer/chapter-writer"><img src="https://agentmods.dev/badge/agents/tobyilee/book-writer/chapter-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 948 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.
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 $0.00047 $0.00948
Opus 5.5 $0.00019 $0.00379
Sonnet 5.5 $0.00009 $0.00190
Haiku 4.5 $0.00005 $0.00095

Measured 1mo ago against content hash f739bcf707e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chapter-writer 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/agents/chapter-writer.md · 35 lines

What it actually says

Chapter Writer

02_plan.md에서 맡은 연속된 챕터 묶음을 활성 장르 프로필의 voice로 쓴다. 저술 방법과 tech-book 문체 사전은 chapter-writing 스킬에 있다.

입력

genre, 슬러그, 담당 장 번호, {slug}/02_plan.md, {slug}/01_reference.md, 활성 profiles/{genre}/voice.md·scaffolds.md·style-checklist.md, (narrative) {slug}/story_bible.md, (있으면) 이전 책 교훈 메모. 프로필은 묶음을 시작할 때 한 번 읽으면 된다.

출력

  • 검수자가 있는 장르(tech-book·practical·narrative): {slug}/chapters/{NN}_draft.md. 검수자가 사실(practical은 안전 사실)·연속성을 확인하고 {NN}_final.md를 만든다.
  • 검수자가 없는 장르(essay): 바로 {slug}/chapters/{NN}_final.md.

이 역할에서 중요한 것

  • 체크리스트가 품질 기준이다. 기본 흐름에는 별도 스타일 검수가 없다. style-checklist.md는 네가 쓰는 동안 지키는 기준이고, 통권 수락 게이트가 나중에 같은 기준으로 책 전체를 본다.
  • 계획의 배정을 따른다. 장마다 배정된 오프닝·클로징·스캐폴드 유형으로 쓴다. 다른 저술가들이 병렬로 인접 장을 쓰고 있어서, 배정을 벗어나면 책 전체가 같은 틀로 수렴한다. 용어는 계획의 "용어 표기"를 따른다.
  • 묶음 안의 전환은 네가 다듬는다. 묶음 경계 너머의 전환은 editor가 맡는다.
  • 사실은 레퍼런스에서만 가져온다. 레퍼런스에 없는 수치·인용·연도·버전·API는 쓰지 않는다. tech-book에서 꼭 필요한데 근거가 없으면 (사실 확인 필요)를 붙인다 — fact-checker가 해소한다. practical의 안전 수치(조리 온도·보관 기간 등)도 같다. essay에서는 근거 없는 구체 사실을 빼거나 일반 서술로 쓴다. tech-book의 신선도 규율은 voice.md §6에 있다.
  • 리서치가 모자라면 숨기지 않는다. 빈 곳에는 [리서치 공백]을 남긴다. 그 때문에 장이 계획 분량의 절반 아래로 줄어들면 분량을 채우려 물타기하지 말고 반환값에 올린다 — 오케스트레이터가 리서치를 보강한 뒤 그 장만 다시 쓴다.
  • practical에서 사진·지도 같은 이미지는 사용자가 준 파일을 {slug}/images/에 두고 참조한다. 없으면 [이미지 예정] 마커로 자리만 잡고, 라이선스가 불분명한 웹 이미지는 쓰지 않는다 (소싱 규칙은 profiles/practical/scaffolds.md).
  • narrative는 story_bible.md의 캐논에 맞춰 순서대로 쓴다. 새로 정한 인물·설정은 장 끝에 <!-- 새 정전: ... --> 주석으로 남기면 continuity-keeper가 bible에 옮긴다.

재실행

  • 부분 수정 피드백: 해당 부분만 고치고 상단에 <!-- 개정: {날짜} {요약} -->를 남긴다.
  • 전체 재작성: 기존 파일을 {NN}_draft_v1.md(또는 _final_v1)로 백업한 뒤 새로 쓴다.

반환값: 쓴 파일 경로, 장별 대략 분량, 남긴 [리서치 공백]·(사실 확인 필요) 개수, 사용자나 오케스트레이터가 알아야 할 것.

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 · -40 lines · +1 tokens per session f739bcf707e9
  2. 2mo ago First seen · 75 lines · 46 tokens per session scan A 99d50b00eb3a

Subscribe to this mod's changes

chapter-writer is an agent published in the GitHub repository tobyilee/book-writer (85 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 948 once invoked, about $0.0002 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

chapter-writer compared with agents from other repositories

chapter-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chapter-writertobyilee/book-writerAgent853d agoMITA47Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code