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 skills add JansenAnalytics/claudex --skill ocr-documentgit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/ocr-document)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/ocr-document"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/ocr-document.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 5.1 | $0.00066 | $0.00499 |
| Opus 5 | $0.00033 | $0.00249 |
| Sonnet 5 | $0.00013 | $0.00100 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
ocr-document scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
OCR Document Skill
Extract text from PDF/image
SKILL=${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/ocr-document/scripts
# Auto-detect best method (text vs OCR)
python3 $SKILL/extract.py document.pdf
# Force OCR (for scanned documents)
python3 $SKILL/extract.py document.pdf --method ocr --lang nor+eng
# Extract tables (pdfplumber)
python3 $SKILL/extract.py document.pdf --method pdfplumber
# Specific pages
python3 $SKILL/extract.py document.pdf --pages 1-5
# Save to file
python3 $SKILL/extract.py document.pdf --output extracted.md
# OCR an image
python3 $SKILL/extract.py photo.jpg --lang nor+eng
Download Telegram files
# Download by file_id
python3 $SKILL/telegram_file.py --file-id <id> --output file.pdf
# Get most recent document from a chat
python3 $SKILL/telegram_file.py --chat-id <your-telegram-user-id> --recent --output file.pdf
Methods
- auto: Try text extraction first, fall back to OCR if low text content
- text: PyMuPDF direct extraction (fastest)
- pdfplumber: Better for tables and structured data
- ocr: Tesseract OCR via pdf2image (for scanned docs)
- hybrid: Text first, OCR only for pages that need it
Languages
Default: nor+eng (Norwegian + English). Change with --lang.
Available: tesseract --list-langs
What ships with it
2 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.
- 3d ago First seen · 62 lines · 66 tokens per session scan A 787610876d3f
ocr-document is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 499 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ocr-scanner
An optical character recognition tool that extracts text from images and PDFs, including text in multiple languages and tables.
paddleocr-mcp
Use the local PaddleOCR MCP SDK v2 server for image OCR, PDF/document parsing, screenshots, tables, and structured text extraction.
paddleocr-doc-parsing
A document-parsing tool configuration for extracting structured Markdown or JSON from complex PDFs and document images, including tables, formulas, charts, and multi-column pages.
paddleocr-text-recognition
An optical character recognition tool configuration for extracting text from images, photos, scans, screenshots, and scanned PDFs. OCR means converting text visible in an image into machine-readable text.
document-query
Use when reading, extracting, summarizing, comparing, or answering questions over local or remote documents, code files, PDFs, Office files, HTML/text files, large text-heavy files, and fallback OCR for document images or scans when vision tools are unavailable or insufficient.
figure-remap
Extract single figures from PDF textbooks on-demand with built-in QC verification. Primary use: when writing/supplementing a note that needs an embedded figure (anatomy, classification, algorithm, imaging). Each call checks an existing fast-path crop, re-extracts from PDF if missing/wrong, retries with local-vision…