Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lfurze/claude-skillsnpx agentmods add skills/lfurze/claude-skills/book-editorWrote 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.
[](https://agentmods.dev/skills/lfurze/claude-skills/book-editor)<a href="https://agentmods.dev/skills/lfurze/claude-skills/book-editor"><img src="https://agentmods.dev/badge/skills/lfurze/claude-skills/book-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.
<a href="https://agentmods.dev/skills/lfurze/claude-skills/book-editor"><img src="https://agentmods.dev/badge/skills/lfurze/claude-skills/book-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.01940 |
| Opus 5 | $0.00045 | $0.00970 |
| Sonnet 5 | $0.00018 | $0.00388 |
| Haiku 4.5 | $0.00009 | $0.00194 |
Grade A, and why
book-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 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.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Editor
Professional editing workflow for manuscripts and long-form documents using Word track changes and comments.
Overview
Book editing uses docx XML editing to produce proper Word track changes. The author can accept/reject each change in Word.
Editing process:
- Calibration — Edit a small sample, get author feedback, establish preferences
- Style guide creation — Document decisions for consistency across chunks
- Multi-pass editing — Work through manuscript in chunks, one pass type at a time
- Final review — Verify consistency and completeness
Before Starting
- Read the technical reference section below for docx XML editing mechanics
- Create a style guide using template in
references/style-guide-template.md - Confirm with author: chunk size, editing priorities, any style preferences
Pass Types
Work through the manuscript one pass type at a time, completing all chunks before moving to the next pass.
Pass 1: Structural/Developmental
Focus: Big picture — chapter organization, argument flow, gaps, redundancies, pacing.
Output: Comments only (no track changes). Flag issues for author decision:
- "This section repeats the argument from Chapter 3"
- "Consider moving this earlier to establish context"
- "Gap: the transition from X to Y needs bridging"
Pass 2: Line Editing
Focus: Paragraph-level clarity — sentence flow, transitions, tightening prose, cutting flab.
Output: Track changes for concrete improvements. Comments for questions:
- Track change: Restructure awkward sentences
- Track change: Cut redundant phrases
- Comment: "This paragraph could go two ways — do you want to emphasize X or Y?"
Pass 3: Copy Editing
Focus: SPAG, consistency, fact-checking, formatting.
Output: Primarily track changes. Comments for queries:
- Track change: Spelling, grammar, punctuation fixes
- Track change: Consistency corrections (per style guide)
- Comment: "Please verify this date/name/statistic"
Pass 4: Final Polish
Focus: Catch anything missed, final read-through.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 225 lines · 90 tokens per session scan A d9d3e23379f3
book-editor is a skill published in the GitHub repository lfurze/claude-skills (23 stars, last pushed 6mo ago), licensed MIT. It adds 90 tokens to every session and 1,940 once invoked, about $0.0005 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.