OpenCUA: Instructions file for Claude Code

CLAUDE.md

OpenCUA CLAUDE.md is an instructions file for Claude Code from xlang-ai/OpenCUA. It costs 1,409 tokens per session, scanned B, original, MIT.

Repository instructions for OpenCUA, an open-source framework for building computer-use agents that operate graphical interfaces. They document the project, setup commands, data processing, and model inference.

In plain words
What is it for?
Use them to set up dependencies, process agent data, and run OpenCUA models through Hugging Face or a vLLM server.
Why use it?
They give a coding agent the project context and the commands needed to prepare the environment and run OpenCUA models. This reduces guesswork when working in the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is xlang-ai/OpenCUA's own configuration. It tells Claude Code how to work on OpenCUA itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenCUA configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xlang-ai/OpenCUA. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xlang-ai/OpenCUA/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/xlang-ai/OpenCUA

Made for: Claude Code.

Wrote 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.

agentmods badge for OpenCUA CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xlang-ai/opencua/claude-md.svg)](https://agentmods.dev/instructions/xlang-ai/opencua/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xlang-ai/opencua/claude-md"><img src="https://agentmods.dev/badge/instructions/xlang-ai/opencua/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,409 This file is loaded in full into every session.
When invoked 1,409 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01409 $0.01409
Opus 5 $0.00705 $0.00705
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 8d ago against content hash 2829e87fb7bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

OpenCUA 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 8d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt-get install -y xvfb
CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

OpenCUA is an open-source framework for scaling computer-use agent data and foundation models. It consists of:

  • AgentNet: Large-scale dataset (22.6K+ tasks) across Windows, macOS, and Ubuntu
  • AgentNetTool: Cross-platform GUI recording and annotation tool (Git submodule in tool/)
  • OpenCUA Models: End-to-end foundation models (7B, 32B, 72B variants) based on Qwen2.5-VL

Commands

Environment Setup

conda create -n opencua python=3.10
conda activate opencua

# Model inference dependencies
pip install -r model/requirement.txt

# Data processing dependencies
pip install -r data/data-process/requirements.txt

# Headless server support (for video processing)
sudo apt-get install -y xvfb

Model Inference

HuggingFace:

cd model/inference
python huggingface_inference.py

vLLM Server (recommended for production):

CUDA_VISIBLE_DEVICES=1,2,3,4 vllm serve /path/to/OpenCUA-32B \
  --trust-remote-code \
  --tensor-parallel-size 4 \
  --served-model-name opencua-32b \
  --host 0.0.0.0 \
  --port 8000

Data Processing Pipeline

Stage 1: Extract raw trajectories from video/events:

cd data/data-process
xvfb-run -a ./scripts/extract_raw.sh -1    # all samples
xvfb-run -a ./scripts/extract_raw.sh 10    # first 10 samples

Stage 2: Standardize to unified schema:

xvfb-run -a ./scripts/raw_to_standardized.sh -1

Stage 3: Generate CoT (requires API_KEY env var):

cd data/cot-generate
export API_KEY="your-api-key"
python gen_cot.py \
  --traj_path ./gen_cot_example/raw_example.jsonl \
  --image_folder ./gen_cot_example/images \
  --output_dir ./gen_cot_example/output/tasks \
  --model claude-3-7-sonnet-20250219

Visualization

cd data/vis
streamlit run app.py -- --traj_file <TRAJ_JSONL> --meta_file <META_JSONL> --image_dir <IMAGES>

Read the full file on GitHub · 183 lines

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. 8d ago First seen · 183 lines · 1,409 tokens per session scan B 2829e87fb7bd

Subscribe to this mod's changes

OpenCUA CLAUDE.md is an instructions file published in the GitHub repository xlang-ai/OpenCUA (833 stars, last pushed 3mo ago), licensed MIT. It adds 1,409 tokens to every session, about $0.0070 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens