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/nameetp/pdfmux/claude-mdgit clone --depth 1 https://github.com/NameetP/pdfmuxWrote 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/nameetp/pdfmux/claude-md)<a href="https://agentmods.dev/instructions/nameetp/pdfmux/claude-md"><img src="https://agentmods.dev/badge/instructions/nameetp/pdfmux/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 | $0.00333 | $0.00333 |
| Opus 5 | $0.00167 | $0.00167 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
pdfmux 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
pdfmux — Agent Instructions
Project
PDF extraction that checks its own work. Multi-pass pipeline: fast extract → audit → selective OCR → merge.
- Language: Python 3.11+
- Build: hatchling (pyproject.toml)
- Lint: ruff
- Test: pytest
- Site: static HTML in
site/(no build step)
Commands
# Python
ruff check src/ tests/ # lint
ruff format src/ tests/ # format
pytest -v # test
# Site
python3 design-system/lint.py site/ # design system lint
npx serve site/ -l 3456 # local dev server
Design System
When editing any file in site/, you MUST follow the design system.
- Read
design-system/DESIGN_SYSTEM.mdfor all visual rules - Read
design-system/SKILL.mdfor agent-specific instructions - After changes, run
python3 design-system/lint.py site/and fix all violations
Key rules:
- No raw hex/rgb/hsl colors outside
:root— use CSS custom properties - No inline
font-family— usevar(--font)orvar(--mono) - Border-radius: only
4px,8px, or10px - Transitions: only
0.15sduration - No external CSS or JS — site is self-contained HTML
- Max content width:
720px
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 · 41 lines · 333 tokens per session scan A a5358584dded
pdfmux CLAUDE.md is an instructions file published in the GitHub repository NameetP/pdfmux (81 stars, last pushed 2d ago), licensed MIT. It adds 333 tokens to every session, about $0.0017 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 2026-08-30.
Other instructions, from other repositories
textbook-to-note AGENTS.md
Instructions for drpwchen/textbook-to-note, covering agents.md — instructions for your ai coding agent, what you're setting up, step 1: which profile is the user setting up?, step 1.1: understand the user's situation and step 2: install dependencies.
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.
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.
tablepack AGENTS.md
Instructions for kujiangmudao/tablepack, covering two user paths, multimodal requirement, environment, hard requirements (never skip) and qc checklist (every pdf).
harborclerk AGENTS.md
AGENTS.md instructions for r0shi/harborclerk, covering agents.md, what this is, non-negotiables, working agreement and review policy.
use_cninfo CLAUDE.md
Instructions for rollysys/use_cninfo, covering claude.md, 这个 repo 是什么, 常用命令, 开发环境 and 跑测试(离线,32 个).