Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/masterleopold/book-capture/claude-mdgit clone --depth 1 https://github.com/masterleopold/book-captureWrote 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/instructions/masterleopold/book-capture/claude-md)<a href="https://agentmods.dev/instructions/masterleopold/book-capture/claude-md"><img src="https://agentmods.dev/badge/instructions/masterleopold/book-capture/claude-md.svg" alt="Measured on agentmods" 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 | $0.01109 | $0.01109 |
| Opus 5 | $0.00554 | $0.00554 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
book-capture CLAUDE.md 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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
A Claude Code plugin: captures book pages from Mac Kindle, Apple Books, Kindle Cloud Reader, PDF, or photos of a physical book, OCRs them, and generates thematic Obsidian Markdown. macOS only.
Reference
- README.md — what it does, install, requirements, the eight
/book-capture:*commands, output shape, settings fields, troubleshooting - docs/architecture.md — layers, command/agent mechanics, stage file contracts, per-source capture details, known inconsistencies
- docs/page-images.md — why WebP, the migration script, photo orientation and ordering in full
- CONTRIBUTING.md — fork/PR flow
Development
No build, no tests, no CI. Verification is running the thing.
bash scripts/setup.sh # npm install + compile vision-ocr + playwright chromium
bash scripts/setup.sh --check-only # exit 1 if deps missing; every command runs this first
claude plugin validate ./ # manifest / frontmatter check
claude --plugin-dir ./book-capture # load this working copy and exercise the commands
Scripts are ESM .mjs run directly with node, and each prints its usage on bad args — the fastest loop for anything below the prompt layer:
node scripts/import-photos.mjs <photo-dir> --output-dir <dir> --dry-run
node scripts/extract-text.mjs <captures-dir> --concurrency 5 --claude-threshold 0.6
ensureVisionOCR only checks that scripts/vision-ocr exists, so after editing vision-ocr.swift, rm scripts/vision-ocr or run setup.sh — only setup.sh compares mtimes. A stale binary otherwise keeps serving the old OCR silently. That binary and scripts/node_modules/ are gitignored.
macOS is load-bearing: screencapture, osascript, inline swift/swiftc, mdls. Poppler (brew install poppler) for PDF only.
Conventions
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.
- 5d ago First seen · 58 lines · 1,109 tokens per session scan A ed6ad228329a
book-capture CLAUDE.md is an instructions file published in the GitHub repository masterleopold/book-capture (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,109 tokens to every session, about $0.0055 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 2026-08-31.
Other instructions, from other repositories
handelsregister-cli CLAUDE.md
Claude Code instructions for DespotB/handelsregister-cli, a project described as: Search the German commercial register (Handelsregister) and download all registry documents: Gesellschafterliste, Gesellschaftsvertrag, AD/CD/HD printouts, structured XML (SI). Python library + CLI, no API key needed.
PDF-Writer CLAUDE.md
Instructions for galkahana/PDF-Writer, covering claude code context - pdf-writer development guide, project overview, coding standards discovered, project structure and key components.
notebooklm-wiki-pipeline CLAUDE.md
Instructions for capitalparser/notebooklm-wiki-pipeline, covering 05notebooklmwikipipeline — 프로젝트 컨텍스트, 핵심 문제, 아키텍처, 도구 구성 and 슬래시 커맨드.
zotero-fulltext-mcp AGENTS.md
AGENTS.md instructions for matthiaskloft/zotero-fulltext-mcp, covering agents.md, project shape, configuration contract, data safety rules and development commands.
justfill-mcp GEMINI.md
Gemini CLI instructions for mrmaciej1/justfill-mcp, covering justfill — filling pdf forms, workflow, auth and conventions.
DocNav-MCP CLAUDE.md
Instructions for shenyimings/DocNav-MCP, covering docnav mcp server, project description, key features, architecture and development guidelines.