book-writer: Skill for Claude Code

.claude/skills/manuscript-acceptance/SKILL.md

manuscript-acceptance is a skill for Claude Code from tobyilee/book-writer. It costs 123 tokens per session (2,519 once invoked), scanned A, original, MIT.

A final whole-book review performed by a separate reviewer before the EPUB is built. It checks the complete manuscript against its plan, records, and stated promises.

In plain words
What is it for?
Use it as a release gate for novels, essays, practical books, and technical books, producing an acceptance report with a result for each review criterion.
Why use it?
It helps catch missing or extra chapters, unresolved markers, open fact checks, broken references, terminology problems, and other issues that can remain after chapter-level editing.

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/manuscript-acceptance/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 manuscript-acceptance

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tobyilee/book-writer/manuscript-acceptance"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/manuscript-acceptance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,519 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 $0.00123 $0.02519
Opus 5 $0.00062 $0.01260
Sonnet 5 $0.00025 $0.00504
Haiku 4.5 $0.00012 $0.00252

Measured 9d ago against content hash 3d52a0b3f7ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

manuscript-acceptance 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 9d 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/manuscript-acceptance/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manuscript Acceptance

통합 원고(04_manuscript.md)가 표지·EPUB 빌드(Phase 5)로 넘어가기 전, 책 전체를 한 번에 검수하는 마지막 게이트다. editor가 쓴 원고를 editor 본인이 승인하면 self-approve가 되므로, 이 절차는 fresh context(manuscript-reviewer)가 수행한다. 챕터 단위 fact/continuity 루프를 다시 돌리지 않고, 통권 단위 문제와 잔여 미결만 본다.

장르 무관. tech-book·narrative·practical·essay 모두에서 Phase 4.5로 실행된다. 장르마다 존재하는 로그가 다르므로(essay엔 factcheck/continuity 로그가 없을 수 있음), 없는 로그가 대상인 기준은 N/A PASS로 처리하고 이유를 한 줄 남긴다.

입력

  • {slug}/04_manuscript.md — 검수 대상 통합 원고
  • {slug}/02_plan.md — 챕터 완비·약속 대조 기준
  • {slug}/factcheck_log.md — (tech-book) (c) 대조
  • {slug}/continuity_log.md — (narrative) 잔여 모순·미회수 복선 대조
  • {slug}/style_log.md — style 잔여 이슈·미합의 대조
  • {slug}/book_manifest.jsonlogline/description 약속 대조
  • {slug}/length_report.md — (있으면) 분량 균형 (a)

수락 기준 체크리스트 (실행형)

ID 기준 어떻게 확인하나 판정 BLOCK 시
(a) 챕터 완비·분량 균형 02_plan.md의 챕터 목록 ↔ 원고의 # N장 헤딩을 1:1 대조. 누락·초과 확인. length_report.md(있으면)로 챕터 분량 편차 점검(한 장이 평균의 ½ 미만/2배 초과면 플래그) 해당 챕터 → Phase 4 (최대 1라운드)
(b) 미해소 마커 0건 원고 전체를 grep으로 훑어 금지 마커 검출 (아래 절차) HARD STOP → 사용자
(c) 사실 미결 해소 factcheck_log.md에서 "미해소"/"재확인"//🕒 잔여 항목, 특히 suspect citation(arXiv ID·인용·URL)이 닫혔거나 사용자 승인됐는지 확인 HARD STOP → 사용자
(d) 용어 통일 + 챕터 간 변주 핵심 용어의 표기 흔들림(영/한, 축약/풀) 통권 점검. 오프닝·클로징·말버릇(tic)이 챕터마다 같은 틀로 반복되는지 점검 해당 챕터 → Phase 4 (최대 1라운드)
(e) 상호 참조 무결성 "앞서 N장에서 ~"/"N장에서 다룬" 류 콜백을 모두 찾아, 실제 그 장에 그 내용이 있는지 대조. 끊긴·잘못된 번호 검출 해당 챕터 → Phase 4 (최대 1라운드)
(f) 약속 이행 매니페스트 logline/description이 약속한 범위·대상·핵심 약속을 원고가 실제로 다루는가 editor 보강 / 미달 시 사용자
(g) front/back matter 완비 서문·목차·콜로폰(## 판권)·에필로그·(tech-book/essay면) 참고문헌이 모두 있는가 editor 보강

절차

  1. 준비genre와 슬러그를 확인하고, 위 입력 중 존재하는 로그를 파악한다. 없는 로그가 대상인 기준은 N/A로 미리 표시.
  2. 마커 스캔 (b) — 원고에서 금지 마커를 grep한다. 0건이어야 한다.
    grep -nE "\(사실 확인 필요\)|\[리서치 공백\]|\[미완성\]" {slug}/04_manuscript.md
    
    • 한 건이라도 나오면 (b) BLOCK = HARD STOP. 줄 번호와 원문을 05_acceptance.md에 기록.
  3. 챕터 완비·분량 (a) — 플랜의 챕터 목록과 원고 # N장 헤딩을 대조.
    grep -nE "^# [0-9]+장" {slug}/04_manuscript.md
    
    • 누락/초과 챕터가 있으면 (a) BLOCK. length_report.md(있으면)로 분량 편차 플래그.
  4. 상호 참조 (e) — 콜백 표현을 모두 뽑아 가리키는 장이 맞는지 확인.
    grep -nE "앞서 [0-9]+장|[0-9]+장에서 (다룬|살펴본|본)" {slug}/04_manuscript.md
    
    • 잘못된 번호·끊긴 참조는 (e) BLOCK.
  5. 에스컬레이션 로그 교차 읽기 (c)factcheck_log.md(+ narrative면 continuity_log.md, 공통으로 style_log.md)에서 잔여 미결을 찾는다.
    grep -nE "미해소|재확인|❌|🕒" {slug}/factcheck_log.md
    
    • 재검증을 새로 하지 않는다. 챕터 루프가 "해소"로 닫은 항목은 신뢰하고, "미해소/재확인"으로 남긴 것만 본다. suspect citation(arXiv ID·인용·URL)은 특히 닫혔는지 확인 — 미검증이면 (c) HARD STOP.
    • continuity_log.md의 "미해소(모순 위험)"/미회수 복선, style_log.md의 미합의 잔여는 통권 영향이 있으면 (d)나 (e)로 흡수해 판정.
  6. 용어·변주 (d) — 통권을 훑어 핵심 용어 표기 흔들림, 오프닝/클로징/tic의 단조 반복을 점검.
  7. 약속·부속 자료 (f)(g) — 매니페스트 logline/description 대조, 서문·목차·콜로폰·에필로그·참고문헌 존재 확인.
  8. 기록 + 평결05_acceptance.md에 기준 표 + 평결 + 차단 항목별 조치를 쓰고, 라우팅 메시지를 SendMessage로 보낸다.

Read the full file on GitHub · 112 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. 9d ago First seen · 112 lines · 123 tokens per session scan A 3d52a0b3f7ed

Subscribe to this mod's changes

manuscript-acceptance is a skill published in the GitHub repository tobyilee/book-writer (81 stars, last pushed 22d ago), licensed MIT. It adds 123 tokens to every session and 2,519 once invoked, about $0.0006 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens