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 skills/abilityai/cornelius/multi-format-book-extractornpx skills add Abilityai/cornelius --skill multi-format-book-extractorgit clone --depth 1 https://github.com/Abilityai/corneliusWrote 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/abilityai/cornelius/multi-format-book-extractor)<a href="https://agentmods.dev/skills/abilityai/cornelius/multi-format-book-extractor"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/multi-format-book-extractor.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 | $0.00075 | $0.00993 |
| Opus 5 | $0.00037 | $0.00496 |
| Sonnet 5 | $0.00015 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
multi-format-book-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Format Book Extractor
Extract chapters from PDF, MOBI, and AZW3 files into individual numbered markdown files. Mirrors the epub-chapter-extractor pattern for non-EPUB formats.
Dependencies
- PDF:
pymupdf— auto-installed via--with pymupdf - Scanned PDF OCR fallback:
requests(--with requests) + a Gemini key in$GEMINI_API_KEY/$GOOGLE_API_KEY(read fromcornelius-internal/.envif unset) - MOBI / AZW3: calibre must be installed
brew install --cask calibre
Single Book
cd $PROJECT_ROOT/.claude/skills/multi-format-book-extractor && \
uv run --with pymupdf --with requests python extract_book.py "/path/to/book.pdf" [output_dir]
If output_dir is omitted, creates a folder named after the file in the same directory.
Scanned / Image-Only PDFs (auto-OCR)
Some PDFs are pure page scans with no text layer — pymupdf extracts nothing
and would silently write empty files. extract_book.py now samples the text layer
first (_has_text_layer) and, when a PDF looks image-only, automatically routes it
to Gemini 2.5 Flash OCR (ocr_pdf.py).
- Renders each page to PNG (~180 DPI), batches pages per API call, transcribes
verbatim to Markdown (preserves verse line breaks, Sanskrit/Tibetan diacritics,
footnotes), and writes
NN_pages-S-E.mdchunk files. - Resumable: re-running skips chunk files already written (≥200 chars), so an interrupted long book picks up where it left off.
- Cost is ~$0.002/page on Flash (a 300-page book ≈ $0.60).
Run OCR directly (e.g. to tune params or force it):
cd $PROJECT_ROOT/.claude/skills/multi-format-book-extractor && \
uv run --with pymupdf --with requests python ocr_pdf.py "/path/to/scan.pdf" [output_dir] \
[--model gemini-2.5-flash] [--dpi 180] [--pages-per-call 5] [--pages-per-file 20] [--concurrency 6]
Batch Extraction (Parallel)
Extract all PDFs, MOBIs, and AZW3s from a directory in parallel:
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.
- 4d ago First seen · 95 lines · 75 tokens per session scan A 0bfbe65c3115
multi-format-book-extractor is a skill published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 75 tokens to every session and 993 once invoked, about $0.0004 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
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…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
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…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.