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/intelligentelectron/pdf-analyzer/claude-mdgit clone --depth 1 https://github.com/IntelligentElectron/pdf-analyzerWrote 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/intelligentelectron/pdf-analyzer/claude-md)<a href="https://agentmods.dev/instructions/intelligentelectron/pdf-analyzer/claude-md"><img src="https://agentmods.dev/badge/instructions/intelligentelectron/pdf-analyzer/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 | $0.01897 | $0.01897 |
| Opus 5 | $0.00949 | $0.00949 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade B, and why
pdf-analyzer CLAUDE.md scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
Point `.mcp.json`'s HTTP MCP entry at `http://localhost:8080/mcp`. When the proxy stops, the MCP disconnects until you start it again. No secrets live in `.mcp.json` — auth is handled per-request by the proxy against you How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Analyzer MCP Server
CRITICAL: Branch Protection
NEVER push directly to main. ALL changes must go through a PR.
- Create a feature branch:
git checkout -b <branch-name> - Make changes and commit
- Push the branch:
git push -u origin <branch-name> - Create PR:
gh pr create
If you accidentally commit to main locally, fix it:
git branch <branch-name> # Create branch from current commit
git reset --hard origin/main # Reset main to match remote
git checkout <branch-name> # Switch to your branch
git push -u origin <branch-name> # Push and create PR
CRITICAL: Model Configuration
Models per provider (do not change without discussion). Users choose during --setup:
- Google Gemini:
gemini-3-flash-preview(fast) /gemini-3.1-pro-preview(flagship) - Anthropic Claude:
claude-sonnet-4-6(fast) /claude-opus-4-7(flagship) /claude-opus-4-6(previous flagship, still selectable) - OpenAI:
gpt-5.4-mini(fast) /gpt-5.4(flagship)
Thinking/reasoning is set to minimum for all models (document analysis doesn't benefit from extended thinking).
References (Google File API for large PDFs):
- https://ai.google.dev/gemini-api/docs/document-processing
- https://ai.google.dev/gemini-api/docs/document-processing#large-pdfs
- https://ai.google.dev/gemini-api/docs/files
Overview
Standalone MCP server for analyzing PDF documents using AI. Supports multiple LLM providers (Google Gemini, Anthropic Claude, OpenAI) via the Vercel AI SDK. Distributed as self-updating binaries for all platforms. Users choose their provider and provide an API key during setup.
Build & Package
Uses Bun to compile TypeScript into standalone executables:
# Build all platforms
npm run compile:all
# Or individual platforms
bun build src/index.ts --compile --target=bun-darwin-arm64 --outfile=bin/pdf-analyzer-darwin-arm64
bun build src/index.ts --compile --target=bun-darwin-x64 --outfile=bin/pdf-analyzer-darwin-x64
bun build src/index.ts --compile --target=bun-linux-arm64 --outfile=bin/pdf-analyzer-linux-arm64
bun build src/index.ts --compile --target=bun-linux-x64 --outfile=bin/pdf-analyzer-linux-x64
bun build src/index.ts --compile --target=bun-windows-x64 --outfile=bin/pdf-analyzer-windows-x64.exe
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 · 203 lines · 1,897 tokens per session scan B 5700df7237d2
pdf-analyzer CLAUDE.md is an instructions file published in the GitHub repository IntelligentElectron/pdf-analyzer (4 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,897 tokens to every session, about $0.0095 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
docs-to-pdf CLAUDE.md
Claude Code instructions for jean-humann/docs-to-pdf, covering claude development guide for docs-to-pdf, project overview, development environment setup, using mise (recommended) and install mise (if not already installed).
PDF-Writer CLAUDE.md
Instructions for galkahana/PDF-Writer, covering claude code context - pdf-writer development guide, project overview, coding standards discovered, project structure and key components.
autorename-pdf CLAUDE.md
Instructions for ptmrio/autorename-pdf, covering autorename-pdf, development setup, source venv/bin/activate # linux/macos, commands and ai tool integration.
pdfnative-mcp AGENTS.md
Instructions for Nizoka/pdfnative-mcp, covering agents.md — pdfnative-mcp, 1. tool catalogue (28 tools), 2. decision tree, 3. token-frugal responses and 4. output modes & environment.
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.
notebooklm-wiki-pipeline CLAUDE.md
Instructions for capitalparser/notebooklm-wiki-pipeline, covering 05notebooklmwikipipeline — 프로젝트 컨텍스트, 핵심 문제, 아키텍처, 도구 구성 and 슬래시 커맨드.