pdf-expert

pdf-expert is a skill for Claude Code from sandraschi/pdf-mcp. It costs 0 tokens per session (949 once invoked), scanned A, original, MIT.

A set of tools for extracting information from PDF files, changing their structure, adding annotations, converting them, checking them, and searching them for relevant content.

In plain words
What is it for?
Use it to extract text, images, tables, links, fonts, metadata, and outlines; merge, split, rotate, reorder, delete, compress, encrypt, or decrypt pages; and add annotations or search PDF content.
Why use it?
It gathers common PDF tasks in one place instead of requiring separate tools for reading text, handling pages, inspecting metadata, or marking up documents.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pdf-mcp plugin — 2 skills, 1 MCP server shipped together

Good fit Use it to extract text, images, tables, links, fonts, metadata, and outlines; merge, split, rotate, reorder, delete, compress, encrypt, or decrypt pages; and add annotations or search PDF content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandraschi/pdf-mcp/pdf-expert
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.

Any agent
npx skills add sandraschi/pdf-mcp --skill pdf-expert
Clone the repo
git clone --depth 1 https://github.com/sandraschi/pdf-mcp

Made for: Claude Code.

Or install pdf-mcp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

agentmods badge for pdf-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandraschi/pdf-mcp/pdf-expert.svg)](https://agentmods.dev/skills/sandraschi/pdf-mcp/pdf-expert)
Your own site
<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>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00949
Opus 5 $0.00000 $0.00475
Sonnet 5 $0.00000 $0.00190
Haiku 4.5 $0.00000 $0.00095

Measured 7d ago against content hash a874e7dca660, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

pdf_mcp/skills/pdf-expert/SKILL.md · 82 lines

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 pages
  • images — extract embedded images with dimensions and format info
  • tables — extract tabular data via pdfplumber
  • metadata — extract title, author, dates, page count, file size
  • fonts — list fonts used in the document
  • links — extract hyperlinks with page and coordinates
  • outline — extract table of contents as a nested tree

pdf_manipulate — Modify PDF structure

  • merge — combine multiple PDFs into one
  • split — split into individual pages or page ranges
  • rotate — rotate pages by specified angle
  • reorder — rearrange pages in a new order
  • delete_pages — remove specific pages
  • compress — reduce file size via image downscaling
  • encrypt — password-protect a PDF
  • decrypt — remove password protection
  • optimize — 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 coordinates
  • highlight — highlight all occurrences of search text
  • underline — underline all occurrences of search text
  • header_footer — add repeating header and footer text
  • page_numbers — add page numbers with configurable position and start

pdf_forms — Handle form fields

  • list_fields — enumerate all interactive form fields
  • fill — fill form fields with values
  • flatten — 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 Markdown
  • to_images — render each page as PNG or JPEG
  • to_html — extract text as simple HTML
  • from_html — create PDF from HTML content
  • from_markdown — create PDF from Markdown content
  • from_images — create PDF from image files (one per page)

Read the full file on GitHub · 82 lines

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. 7d ago First seen · 82 lines · 0 tokens per session scan A a874e7dca660

Subscribe to this mod's changes

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.