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 sandraschi/pdf-mcp --skill pdf-expertgit clone --depth 1 https://github.com/sandraschi/pdf-mcpWrote 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/sandraschi/pdf-mcp/pdf-expert)<a href="https://agentmods.dev/skills/sandraschi/pdf-mcp/pdf-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/pdf-mcp/pdf-expert.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 | $0.00000 | $0.00949 |
| Opus 5 | $0.00000 | $0.00475 |
| Sonnet 5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
pdf-expert 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 7d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pdf-mcp Skill
Overview
pdf-mcp is a full-stack PDF intelligence MCP server. It provides 40+ operations across 7 portmanteau tools for extracting, manipulating, annotating, converting, validating, and RAG-searching PDF documents. Use it whenever the user needs to work with PDF files programmatically.
Tool Categories
pdf_extract — Extract content from PDFs
text— extract plain text from one or more pagesimages— extract embedded images with dimensions and format infotables— extract tabular data via pdfplumbermetadata— extract title, author, dates, page count, file sizefonts— list fonts used in the documentlinks— extract hyperlinks with page and coordinatesoutline— extract table of contents as a nested tree
pdf_manipulate — Modify PDF structure
merge— combine multiple PDFs into onesplit— split into individual pages or page rangesrotate— rotate pages by specified anglereorder— rearrange pages in a new orderdelete_pages— remove specific pagescompress— reduce file size via image downscalingencrypt— password-protect a PDFdecrypt— remove password protectionoptimize— clean and deflate the PDF structure
pdf_annotate — Add markup and annotations
watermark— add text or image watermark (tile, center, corner positions)stamp— add stamp annotation at specific coordinateshighlight— highlight all occurrences of search textunderline— underline all occurrences of search textheader_footer— add repeating header and footer textpage_numbers— add page numbers with configurable position and start
pdf_forms — Handle form fields
list_fields— enumerate all interactive form fieldsfill— fill form fields with valuesflatten— flatten form fields (make them non-interactive)export_data— export field values as JSON
pdf_convert — Convert between formats
to_markdown— extract text with heading detection as Markdownto_images— render each page as PNG or JPEGto_html— extract text as simple HTMLfrom_html— create PDF from HTML contentfrom_markdown— create PDF from Markdown contentfrom_images— create PDF from image files (one per page)
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.
- 7d ago First seen · 82 lines · 0 tokens per session scan A a874e7dca660
pdf-expert is a skill published in the GitHub repository sandraschi/pdf-mcp (1 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 949 tokens. 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 skills, from other repositories
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.
sn-da-non-spreadsheet-analysis
A skill for extracting and analysing content from Word files, PDFs, and PowerPoint presentations. It can work with text, tables, numbers, charts, formatting, and information across multiple documents.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
A PDF document tool for extracting text, tables, and metadata, creating documents, changing pages, adding annotations, and handling forms. A PDF is a fixed-layout document file.
mineru
An AI-Native skill for parsing PDF / Office / image files into clean Markdown with MinerU — a fast, zero-config document parser for AI agents. Works with NO token via the lightweight Agent API and auto-upgrades to the Standard API (token) for large files, batches, and DOCX/HTML/LaTeX export. Use when: (1) Converting…