agentmods.dev

computer-use

computer-use is a skill for Claude Code, Codex from patleeman/neon-pilot. It costs 22 tokens per session (379 once invoked), scanned A, original, MIT.

A guide to controlling native desktop applications through Cua Driver, a tool for sending actions to desktop app windows. For web pages, it recommends using browser automation instead.

In plain words
What is it for?
Use it to capture desktop app state, inspect windows, click controls, type text, and send keys when browser tools cannot handle the task.
Why use it?
It explains how to inspect desktop windows safely and how to recover when accessibility information is incomplete or changes after an action.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 23repo 3mo ago A scan 22 tokens original MIT

Good fit Use it to capture desktop app state, inspect windows, click controls, type text, and send keys when browser tools cannot handle the task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patleeman/neon-pilot/computer-use
View source ↗ patleeman/neon-pilot neonpilot.net
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.

Any agent
npx skills add patleeman/neon-pilot --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/patleeman/neon-pilot

Made for: Claude Code, Codex.

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 computer-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/patleeman/neon-pilot/computer-use/github.svg)](https://agentmods.dev/skills/patleeman/neon-pilot/computer-use)
Your own site
<a href="https://agentmods.dev/skills/patleeman/neon-pilot/computer-use"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/computer-use/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for computer-use

Your own site · 80×15
<a href="https://agentmods.dev/skills/patleeman/neon-pilot/computer-use"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/computer-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00022 $0.00379
Opus 5.5 $0.00009 $0.00152
Sonnet 5.5 $0.00004 $0.00076
Haiku 4.5 $0.00002 $0.00038

Measured 2mo ago against content hash 82d28b3d0e8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

extensions/system-computer-use/skills/computer-use/SKILL.md · 33 lines

What it actually says

Computer Use

Use computer_use for native desktop apps when browser automation is not enough.

Rules:

  • Prefer Workbench Browser or agent-browser for web-only tasks.
  • Start with computer_use(action="capture") or computer_use(action="status").
  • Use window_state for a specific pid and window_id before clicking UI elements.
  • Re-capture after state-changing actions; element indices are stale after UI changes.
  • On macOS, focus_app is informational only; Cua delivers input to the target pid without bringing the app to the foreground.
  • Use type for text fields. For app controls such as calculator operators, prefer click on the AX element; use key for single keys and hotkeys.
  • Never type passwords, recovery codes, API keys, or other secrets.
  • Never click OS permission prompts, payment confirmations, destructive deletion prompts, or login/logout/lock actions without explicit user instruction.
  • If the accessibility tree is sparse, use screenshot coordinates carefully or stop and ask.

Troubleshooting:

  • macOS needs Accessibility and Screen Recording permissions for Cua Driver.
  • Cua Driver is not bundled or auto-installed on first use. It is installed by the Install Cua Driver command, then verified with the Run Computer Use doctor command.
  • The currently tested public workflow uses cua-driver 0.6.8.
  • Windows over SSH may not have an interactive desktop; use an RDP/console session or Cua Driver's autostart pattern.
  • Linux needs a reachable display server and AT-SPI.
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. 2mo ago First seen · 33 lines · 22 tokens per session scan A 82d28b3d0e8d

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository patleeman/neon-pilot (23 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 379 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

computer-use compared with skills from other repositories

computer-use next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
computer-usepatleeman/neon-pilotSkill233mo agoMITA22Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code