LiteParse is a local tool that extracts structured text and layout information from PDF files, including coordinates for each piece of text and optional OCR for scanned pages. It is for applications that need to turn PDFs into Markdown, JSON, or plain text without relying on cloud services.
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/run-llama/liteparse/claude-mdgit clone --depth 1 https://github.com/run-llama/liteparseWrote 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/run-llama/liteparse/claude-md)<a href="https://agentmods.dev/instructions/run-llama/liteparse/claude-md"><img src="https://agentmods.dev/badge/instructions/run-llama/liteparse/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 | $0.00004 | $0.00004 |
| Opus 5 | $0.00002 | $0.00002 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00000 | $0.00000 |
Grade A, and why
liteparse 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 6d 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.
This is a copy
100% identical to deepseek-harness CLAUDE.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
@AGENTS.md
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.
- 6d ago First seen · 1 lines · 4 tokens per session scan A 918b1c905593
liteparse CLAUDE.md is an instructions file published in the GitHub repository run-llama/liteparse (12,255 stars, last pushed today), licensed Apache-2.0. It adds 4 tokens to every session, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deepseek-harness CLAUDE.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
MistralDocAI-mcp AGENTS.md
AGENTS.md instructions for trsdn/MistralDocAI-mcp, covering agent instructions, what this repository is, what this repository is not, layout and setup.
MistralDocAI-mcp copilot-instructions.md
Copilot instructions for trsdn/MistralDocAI-mcp: The instructions for this repository live in AGENTS.md. Read that file. It is tool-neutral and it is the only copy, so this file deliberately restates nothing.
textbook-to-note CLAUDE.md
Instructions for drpwchen/textbook-to-note, covering claude.md — which audience are you?, working on this repo, spec before code, how much ceremony — decide before you start and the commit guard.
websearch-mcpserver AGENTS.md
AGENTS.md instructions for daidaiJ/websearch-mcpserver, covering agents.md — 智能体协作指南, 项目一句话定位, 技术栈速览, 目录结构与模块职责 and 核心数据流.
frameproof AGENTS.md
AGENTS.md instructions for edvardgrishin27/frameproof, covering frameproof, установка and одно правило, которое нельзя обходить.
ocr-mcp AGENTS.md
AGENTS.md instructions for sandraschi/ocr-mcp, covering ocr-mcp — agent guide, entry points, quick ref, standards and key files.