agent-computer-use CLAUDE.md

agent-computer-use CLAUDE.md is an instructions file for coding agents from kortix-ai/agent-computer-use. It costs 956 tokens per session, scanned A, original, MIT.

A set of project instructions for agent-computer-use, a Rust-based command-line tool that lets AI agents interact with computer interfaces.

In plain words
What is it for?
Use it when working on the tool's Rust command-line code, platform backends, browser or Electron support, MCP wrapper, documentation, benchmarks, or build scripts.
Why use it?
It gives contributors a quick reference to the repository layout, setup commands, build process, and documentation areas.

Instructions file

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 instructions/kortix-ai/agent-computer-use/claude-md
Clone the repo
git clone --depth 1 https://github.com/kortix-ai/agent-computer-use

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 agent-computer-use CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kortix-ai/agent-computer-use/claude-md.svg)](https://agentmods.dev/instructions/kortix-ai/agent-computer-use/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kortix-ai/agent-computer-use/claude-md"><img src="https://agentmods.dev/badge/instructions/kortix-ai/agent-computer-use/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 956 This file is loaded in full into every session.
When invoked 956 The same file — it is already loaded in full.
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 $0.00956 $0.00956
Opus 5 $0.00478 $0.00478
Sonnet 5 $0.00191 $0.00191
Haiku 4.5 $0.00096 $0.00096

Measured 5d ago against content hash 24f742dd873b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-computer-use 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.

CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-computer-use

Computer use CLI for AI agents. Built with Rust, distributed via npm.

Repo structure

agent-computer-use/
├── cli/                Rust CLI (Cargo workspace)
│   ├── src/            Main binary, handlers, actions, snapshot, wait, DSL parser
│   └── crates/
│       ├── agent-computer-use-core/  Platform trait, AccessibilityNode, Selector, element utils
│       ├── agent-computer-use-macos/ macOS backend (AXUIElement, CGEvent, batch attribute fetch)
│       ├── agent-computer-use-cdp/   CDP bridge for Electron apps (WebSocket, DOM walker, JS interaction)
│       ├── agent-computer-use-linux/ Linux backend (AT-SPI2)
│       ├── agent-computer-use-windows/ Windows backend (UIAutomation)
│       └── agent-computer-use-mcp/   MCP server wrapper
├── docs/               Next.js docs site
├── benchmark/          E2E benchmarks, stress tests, comparison
├── bin/                JS wrapper + precompiled binaries
├── docker/             Cross-compilation Dockerfiles
├── scripts/            Setup, build, bench scripts
└── .github/            CI/CD workflows

Quick reference

pnpm setup              # first-time setup (checks deps, builds, installs)
pnpm build              # build CLI (release)
pnpm test               # run Rust tests
pnpm lint               # cargo fmt --check + clippy
pnpm format             # auto-format Rust + JS/TS
pnpm dev                # start docs dev server
pnpm check              # lint + test (pre-commit)
pnpm bench              # criterion micro-benchmarks
pnpm bench:e2e          # real-world app benchmarks
pnpm bench:stress       # reliability stress test
pnpm bench:diff         # compare benchmark runs

Working on the CLI

Rust code lives in cli/. The workspace has:

  • agent-computer-use (crate) — produces the agent-cu binary, CLI args, handlers
  • agent-computer-use-core — platform-agnostic types (Platform trait, AccessibilityNode, Selector, element utilities)
  • agent-computer-use-macos — macOS backend (AXUIElement, CGEvent, batch AXUIElementCopyMultipleAttributeValues)
  • agent-computer-use-cdp — CDP bridge (auto-detects Electron, auto-relaunches with debug port, WebSocket connection caching)

Read the full file on GitHub · 91 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. 5d ago First seen · 91 lines · 956 tokens per session scan A 24f742dd873b

Subscribe to this mod's changes

agent-computer-use CLAUDE.md is an instructions file published in the GitHub repository kortix-ai/agent-computer-use (55 stars, last pushed 3mo ago), licensed MIT. It adds 956 tokens to every session, about $0.0048 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.