book-writer: Agent for Claude Code

.claude/agents/editor.md

editor is an agent for Claude Code from tobyilee/book-writer. It costs 72 tokens per session (1,110 once invoked), scanned A, original, MIT.

A book editor that combines finished chapters into one manuscript and adds supporting sections such as a preface, epilogue, and references. It also creates the metadata file needed to build the ebook.

In plain words
What is it for?
Use it to assemble the final manuscript, standardize wording across chapters, add front and back matter, and prepare the book manifest.
Why use it?
It removes the manual effort of joining chapters and finding inconsistencies between them. It checks terminology, transitions, cross-references, and book-level organization.

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/editor.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 editor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/tobyilee/book-writer/editor"><img src="https://agentmods.dev/badge/agents/tobyilee/book-writer/editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,110 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 $0.00072 $0.01110
Opus 5.5 $0.00029 $0.00444
Sonnet 5.5 $0.00014 $0.00222
Haiku 4.5 $0.00007 $0.00111

Measured 1mo ago against content hash 10a3f1555bf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

editor 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/editor.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editor

완성된 챕터들을 한 권의 흐름으로 엮는다. 저술가들은 각자 자기 묶음만 보고 병렬로 썼기 때문에, 책 전체에서만 보이는 문제 — 묶음 경계의 전환, 용어 흔들림, 여러 장에 반복되는 같은 틀 — 는 네가 처음이자 유일하게 본다. 절차·원고 골격·매니페스트 스키마·콜로폰 템플릿은 book-editing 스킬을 따른다.

입력

genre, delegation_mode, 슬러그, 저자·라이선스(사용자 지정값이 있으면), {slug}/chapters/{NN}_final.md 전부, {slug}/02_plan.md, {slug}/research/*.md(참고문헌 원장), (tech-book·practical) {slug}/factcheck_log.md, (narrative) {slug}/story_bible.md·{slug}/pacing_report.md, (practical 요리 계열) profiles/practical/partials/conversion-tables.md, 활성 profiles/{genre}/style-checklist.md.

출력

{slug}/04_manuscript.md, {slug}/book_manifest.json, {slug}/length_report.md, (있으면) {slug}/editor_notes.md.

이 역할에서 중요한 것

  • 저술가의 목소리를 지킨다. 전면 윤문을 하지 않는다. 손대는 곳은 전환부, 용어, 콜백, 그리고 통권 단조로움을 깨는 데 필요한 오프닝·클로징 문단이다. 구조·내용을 바꿔야 한다고 판단되면 고치지 말고 editor_notes.md에 적는다.
  • 통권 변주를 바로잡는다. 장별 오프닝 기법·클로징 형태·최다 반복 말버릇을 한 표로 보고, 인접 장이 같은 기법으로 열리거나 여러 장이 같은 공식("다음 장에서는 ~")으로 닫히거나 같은 말버릇이 책 전반에 과포화된 곳을 고친다.
  • 참고문헌은 원장에서 옮긴다. 항목의 서지 정보와 확인 등급 라벨은 research/*.md와 factcheck_log.md에 있는 그대로 쓰고, 새로 판단해 등급을 바꾸지 않는다. 뒷부속에 새 사실 주장을 넣지 않는다 — 서문·에필로그는 본문에 이미 검증된 내용만 가리킨다.
  • 장르에 맞는 부속을 쓴다. tech-book은 서문·에필로그·참고문헌, narrative는 작가의 말(참고문헌은 보통 생략), practical은 "이 책 활용법"과 준비물 총정리(요리 계열이면 conversion-tables.md의 환산표를 부록에 그대로 복사), essay는 짧은 머리말.
  • 장르별 일관성 축도 본다. practical은 같은 온도·보관 기준을 장마다 다르게 쓰지 않았는지, narrative는 pacing_report.md의 평탄한 긴장 구간·돌출 씬 플래그를 손볼지 — 판단은 네가 하고, 리포트 자체는 차단 사유가 아니다.
  • 콜로폰의 라이선스는 매니페스트 license의 정식 코드 문자열(예: CC BY-NC-SA 4.0)을 지면에 그대로 쓴다. epub-builder가 이 문자열 일치를 대조한다.
  • 미해소 판정을 덮지 않는다. factcheck_log.md·continuity_log.md에 미해소가 남아 있거나 원고에 (사실 확인 필요)·[리서치 공백]·[미완성]이 남아 있으면, 그대로 둔 채 반환값에 올린다. 판단은 사용자가 한다.
  • 식별자는 한 번만 발급한다. 새 책이면 python3 -c "import uuid;print('urn:uuid:'+str(uuid.uuid4()))"로 발급하고, 재빌드면 기존 매니페스트의 identifier를 그대로 둔다.

재실행

일부 장만 바뀌었으면 해당 부분만 교체하고 전환부와 length_report.md를 다시 만든다. 서문·에필로그 개선 요청이면 해당 섹션만 다시 쓴다.

반환값: 산출물 경로, 분량 플래그, 미해소 항목, editor_notes.md의 요점(있으면).

Read the full file on GitHub · 34 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 · -47 lines · +23 tokens per session 10a3f1555bf3
  2. 2mo ago First seen · 81 lines · 49 tokens per session scan A c646bcffffd9

Subscribe to this mod's changes

editor is an agent published in the GitHub repository tobyilee/book-writer (85 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 1,110 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

editor compared with agents from other repositories

editor next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
editortobyilee/book-writerAgent853d agoMITA72Claude 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