computer-use

A Linux desktop-control skill that can inspect visible windows and interact with them using clicks, typing, keyboard shortcuts, and scrolling.

In plain words
What is it for?
Listing windows, reading accessibility targets, capturing screenshots, clicking controls, entering text, and sending keystrokes on Linux/X11 desktops.
Why use it?
It lets an agent operate graphical applications when a task cannot be completed through a command line alone.

Skill for Claude CodeCodex

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 skills/tak-uukti/linux-computer-use/computer-use
Any agent
npx skills add tak-uukti/linux-computer-use --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/tak-uukti/linux-computer-use

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 481 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 $0.00039 $0.00481
Opus 5 $0.00019 $0.00241
Sonnet 5 $0.00008 $0.00096
Haiku 4.5 $0.00004 $0.00048

Measured 2d ago against content hash 661dabca2007, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

computer-use 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 2d 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.

skills/computer-use/SKILL.md · 41 lines

What it actually says

computer-use (Linux/X11)

Quick Start

list_windows                          # → @wN list (title, pid, geometry)
screenshot {window:"@w2"}             # focus + capture; returns @eN AX targets + PNG
click {ref:"@e3"}                     # click an element by ref
type_text {text:"hello"}              # type at cursor
keypress {keys:["Return"]}            # submit

Tools

name use
list_windows enumerate visible windows
screenshot focus window, capture PNG, return AX targets @eN
click click @eN/@wN or x,y; supports button, clickCount
type_text type literal text at cursor
set_text replace @eN text/entry value (AT-SPI; falls back to ctrl+a + type)
keypress press keys/chords (Return, ["Ctrl","A"], ["ctrl+l","Return"])
scroll scroll at ref/coords by scrollY/scrollX pixels
computer_actions run a sequence (≤20) in one call

Pitfalls

  • X11 only. Wayland sessions cannot capture other-app windows or synthesize input.
  • Enable AT-SPI: gsettings set org.gnome.desktop.interface toolkit-accessibility true.
  • Keystrokes go to whatever currently has focus — call screenshot {window} first to focus the target.
  • Mouse cursor physically moves on every click (no stealth pointer).
  • @eN refs are scoped to the bridge process and invalidated by the next screenshot. Re-screenshot after layout changes.
  • AX walk capped at depth 12 / 200 elements per app.
  • Chrome / Electron expose AT-SPI only when launched with --force-renderer-accessibility.
  • LibreOffice needs SAL_USE_COMMON_ONE_ACCESSIBILITY=1 and a real Xorg session (not Xvfb).
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. 2d ago First seen · 41 lines · 39 tokens per session scan A 661dabca2007

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository tak-uukti/linux-computer-use (3 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 481 once invoked, about $0.0002 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 skills, from other repositories

web-navigator

Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.

Plocr/Reasonix-computer-use · 30 tokens

open-computer-use

Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.

iFurySt/open-codex-computer-use · 68 tokens

macos-harness

Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…

browser-use/macos-harness · 71 tokens

tauri-pilot

Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.

mpiton/tauri-pilot · 52 tokens

axstream

Fast deterministic macOS UI automation via replayable macros. Use BEFORE driving any macOS app's UI by hand (clicking/typing via computer-use or screenshots) — if a macro exists, replay finishes the task in seconds with no per-step reasoning; after doing a UI task manually, save it as a macro so the next run is fast.…

milind-soni/axstream · 96 tokens

clawdcursor

FALLBACK ONLY — do not invoke unless you have already ruled out (1) a native API (Gmail API, GitHub API, Slack API …), (2) a CLI (git, gh, aws, npm, curl …), (3) direct file editing, and (4) existing browser automation (Playwright, Puppeteer). Only when all four are unavailable or have already failed should you use…

AmrDab/clawdcursor · 265 tokens