What is computer-use-windows?

A Windows-only computer-control skill with its own bundled runtime and MCP server. It can build itself and set up its Python environment when first run, without requiring a local Claude installation.

For tasks that require controlling a Windows desktop through an AI assistant. It is intended for Windows and includes commands for building and launching its standalone server.

It packages the required runtime and dependencies so the skill can be used on Windows without relying on private application files or separately installed Claude components.

computer-use-windows — Skill for Codex by wimi321

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/wimi321/windows-computer-use-skill

agentmods

npx agentmods add skills/wimi321/windows-computer-use-skill/computer-use-windows

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wimi321/windows-computer-use-skill/computer-use-windows/github.svg)](https://agentmods.dev/skills/wimi321/windows-computer-use-skill/computer-use-windows)

Your own site

<a href="https://agentmods.dev/skills/wimi321/windows-computer-use-skill/computer-use-windows"><img src="https://agentmods.dev/badge/skills/wimi321/windows-computer-use-skill/computer-use-windows/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wimi321/windows-computer-use-skill/computer-use-windows"><img src="https://agentmods.dev/badge/skills/wimi321/windows-computer-use-skill/computer-use-windows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 469 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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00469
Opus 5.5	$0.00014	$0.00188
Sonnet 5.5	$0.00007	$0.00094
Haiku 4.5	$0.00004	$0.00047

Measured 1mo ago against content hash 897a71c419fb, 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-windows 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 1mo ago.

The scan reads SKILL.md. This mod also ships 34 executable files (project/runtime/windows_helper.py, project/src/cli.ts, project/src/computer-use/appNames.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skill/computer-use-windows/SKILL.md · 65 lines

What it actually says

Windows Computer-Use Skill

Use this skill when the task needs a portable Windows computer-use skill bundled with its own standalone runtime and MCP server.

What this skill does

uses the bundled windows-computer-use-skill project under the installed skill directory
builds the standalone MCP server
lets the server auto-bootstrap its Python runtime on first launch
avoids any dependency on local Claude binaries, .node modules, or extracted app assets
stays explicitly Windows-only because the underlying desktop-control backend is Windows-specific

Default bundled project path

After installation, assume the standalone project lives at:

~/.codex/skills/computer-use-windows/project

If the user installed the skill under a custom CODEX_HOME, use that equivalent path instead.

Build

Always build from the bundled project:

cd ~/.codex/skills/computer-use-windows/project
npm install
npm run build

Run

cd ~/.codex/skills/computer-use-windows/project
node dist/cli.js

The first real run will automatically create .runtime/venv and install the public Python dependencies.

Validation notes

Version 0.1.1 fixes the shared system-key blocklist logic so Windows runtime builds use the correct Windows shortcut denylist instead of a broken cross-platform branch.
This project has been statically validated from macOS for TypeScript build health, bundled project integrity, and Python helper syntax, but still needs end-to-end runtime validation on a real Windows machine.

Guardrails

Treat this host as trusted-local only.
Do not tell the user to search their local Claude install for binaries or hidden assets.
Be explicit that this runtime is standalone and uses public dependencies only.
Mention that the current runtime reports screenshotFiltering: none, so action gating is handled at the MCP layer.

Files

What ships with it

47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 65 lines · 36 tokens per session scan A 897a71c419fb

Subscribe to this mod's changes

computer-use-windows is a skill published in the GitHub repository wimi321/windows-computer-use-skill (3 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 469 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 2026-08-31.

Browser automation ai-agents automation computer-use desktop-automation mcp model-context-protocol skill windows

computer-use-macos

Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.

wimi321/macos-computer-use-skill · 37 tokens

exo-control

Use when any AI needs eyes and hands on Windows — desktop UIA, browser CDP, files, registry, OS ops via Exo Control (MCP, CLI, or Python). Harness-agnostic.

ImAvgErix/ExoControl · 46 tokens

computer-use-linux

Top-level Linux computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.

wimi321/linux-computer-use-skill · 35 tokens

workflow-interaction

A guide for exploring and operating real web pages and desktop applications. It describes how to locate the correct window or page, inspect available controls, and confirm that an action succeeded.

mrpulor-gh/nuphus · 0 tokens

workflow-recovery

A recovery guide for workflows that fail during execution, especially when resuming the same run reuses stale captured values such as an old window, query, or screen position. It helps distinguish a temporary runtime blockage from a genuine workflow-design defect.