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 instructions/sandraschi/pdf-mcp/claude-mdgit 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/instructions/sandraschi/pdf-mcp/claude-md)<a href="https://agentmods.dev/instructions/sandraschi/pdf-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/pdf-mcp/claude-md.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 | $0.00148 | $0.00148 |
| Opus 5 | $0.00074 | $0.00074 |
| Sonnet 5 | $0.00030 | $0.00030 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
pdf-mcp CLAUDE.md 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 5d 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
pdf-mcp — Claude / agent context
PDF intelligence MCP. Ports 11130 (frontend) / 11131 (backend).
Do
- Prefer portmanteau tools (
pdf_extract,pdf_manipulate, …) - Use workbench/pipeline for interactive jobs; RAG for corpus Q&A
- Follow
docs/ONBOARDING.md/SPEC.md
Don't
- Index confidential PDFs without Sandra's intent
- Assume cloud OCR is wired
- Commit
data/uploads or LanceDB indexes
Commands
.\start.ps1
just test
just lint
See AGENTS.md, SPEC.md, llms-full.txt.
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.
- 5d ago First seen · 26 lines · 148 tokens per session scan A 14f2d1658a64
pdf-mcp CLAUDE.md is an instructions file published in the GitHub repository sandraschi/pdf-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 148 tokens to every session, about $0.0007 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.
Other instructions, from other repositories
book-to-skill CLAUDE.md
Claude Code instructions for virgiliojr94/book-to-skill, a project described as: Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
document-SKILLs AGENTS.md
AGENTS.md instructions for appautomaton/document-SKILLs, covering document skills, python, python packages, node.js and system tools (brew or apt-get).
ocr-mcp copilot-instructions.md
Copilot instructions for sandraschi/ocr-mcp: You have access to a FastMCP 3.4+ OCR server with 14 backends for document text extraction.
AI_Agent_MCP_Tool_for_Multi_Docu_PDF_PNG_QR_File_Conversion_Processing_Capability AGENTS.md
AGENTS.md instructions for lovecatisgood-sudo/AI_Agent_MCP_Tool_for_Multi_Docu_PDF_PNG_QR_File_Conversion_Processing_Capability, covering agent guidance, scope, required checks, tool changes and fixtures.
md-anything copilot-instructions.md
Instructions for ojspace/md-anything, covering copilot instructions for md-anything, build, test, and lint commands, full suite, contributor-safe required subset and regenerate generated pdf/epub fixtures when needed.
asset-aware-mcp copilot-instructions.md
Copilot instructions for u9401066/asset-aware-mcp, covering copilot 自定義指令, 專案概述, 核心功能, llm 後端 and pdf → 資產引擎選擇 🚦.