pdf

A command that turns a PDF book into page images, extracts text with OCR, and produces structured Markdown. OCR, or optical character recognition, reads text from scanned page images.

In plain words
What is it for?
Use it to capture a book from a PDF, including scanned pages, and create a structured Markdown version. It requires Poppler and may require decrypting an encrypted PDF first.
Why use it?
It handles image-based PDFs whose text cannot be selected or copied. It also checks for embedded text and supports settings such as image resolution.

Command

Install

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.

agentmods
npx agentmods add commands/masterleopold/book-capture/pdf
Clone the repo
git clone --depth 1 https://github.com/masterleopold/book-capture
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 254 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.00254
Opus 5 $0.00006 $0.00127
Sonnet 5 $0.00002 $0.00051
Haiku 4.5 $0.00001 $0.00025

Measured 2d ago against content hash 48e50918d7d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdf 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 2d 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.

commands/pdf.md · 22 lines

What it actually says

PDF Book Capture

Source is pre-selected: pdf (image-based/scanned PDF via Poppler pdftoppm).

Follow the full pipeline in ${CLAUDE_PLUGIN_ROOT}/commands/capture.md with source = pdf. Skip the platform selection step.

PDF-specific notes:

  • Requires Poppler: brew install poppler (provides pdftoppm, pdfinfo, pdftotext)
  • Checks for embedded text — use --force to proceed with image-based PDFs that also have embedded text
  • Encrypted PDFs must be decrypted first: qpdf --decrypt input.pdf output.pdf
  • --dpi: 150 (fast), 200 (balanced, default), 300 (high quality)
node "${CLAUDE_PLUGIN_ROOT}/scripts/capture-pdf.mjs" "<pdf-path>" <BookID> [--dpi 200] --output-dir "<OUTPUT_DIR>"
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. 2d ago First seen · 22 lines · 12 tokens per session scan A 48e50918d7d3

Subscribe to this mod's changes

pdf is a command published in the GitHub repository masterleopold/book-capture (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 254 once invoked, about $0.0001 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.