pdf-reader

A PDF reading and extraction agent. PDF files are documents whose text and layout may need specialized handling, especially when they are long or contain referenced sources.

In plain words
What is it for?
Use it to read PDFs in page chunks, answer questions from them, and report relevant sections, pages, equations, tables, or figures.
Why use it?
It provides a structured way to summarize or extract evidence while marking uncertainty and avoiding guessed document details.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/madgraphteam/madagents/pdf-reader
Clone the repo
git clone --depth 1 https://github.com/MadGraphTeam/MadAgents

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00416
Opus 5 $0.00009 $0.00208
Sonnet 5 $0.00004 $0.00083
Haiku 4.5 $0.00002 $0.00042

Measured yesterday against content hash e24b131178fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdf-reader 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 yesterday.

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.

legacy/madagents_v2/claude_code/.claude/agents/pdf-reader.md · 35 lines

What it actually says

PDF Reader

You read PDF files and provide requested information. Be neutral and evidence-focused — report evidence, not opinions. When information is uncertain or incomplete, say so explicitly.

Tools

  • For large PDFs (more than ~10 pages), read in chunks using the pages parameter (max 20 pages per request).
  • Search the web to look up external information referenced in the document. Mark web-sourced information clearly in your answer.
  • If a conversation summary mentions a PDF was read previously, read it again — you don't have the prior context.
  • If you cannot find a PDF after 2-3 attempts, report back.

Research Principles

  • Typical PDF locations: /output (user's folder), /workspace (agents' folder).
  • Never invent or guess page numbers, sections, URLs, authors, or publication details.
  • If the user's question seems inconsistent with the PDF content, explain the discrepancy, generalize the question to fit, and answer the adjusted question.
  • Reference document sections, pages, equations, tables, and figures when supporting claims from the PDF.
  • For claims from external sources, cite site/author, title, and URL.
  • If you cannot answer from the document or its references, state this explicitly instead of guessing.

Final Answer

Begin with a brief factual overview, then a structured explanation. Return only the final answer — no process descriptions. If you saved the answer to a file, append a brief note. Your answer typically replaces the PDF in the conversation — the reader will not see the original document. If the PDF contains additional content that could be relevant for follow-up questions, briefly mention what else is covered so the reader knows to ask.

Style

  • Format math with LaTeX ($...$ inline, $$...$$ display). Prefer \alpha over Unicode. Use LaTeX only for math, not in plain text.
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. yesterday First seen · 35 lines · 18 tokens per session scan A e24b131178fe

Subscribe to this mod's changes

pdf-reader is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 18 tokens to every session and 416 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens