A guide to building computer-use agents with the CUA framework, which lets an agent operate desktop applications or virtual machines. It covers automation and computer-use models from Anthropic and OpenAI.

It is for automating desktop apps, controlling Linux, Windows, or macOS virtual machines, and integrating computer-use models.

It collects the setup and implementation guidance needed when an agent must work through screens and applications instead of only editing text or code.

How duvoai/cua-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to duvoai/cua-mcp-server. 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/duvoai/cua-mcp-server/main/.claude/skills/cua-cloud/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/duvoai/cua-mcp-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/duvoai/cua-mcp-server/cua-cloud/github.svg)](https://agentmods.dev/skills/duvoai/cua-mcp-server/cua-cloud)

Your own site

<a href="https://agentmods.dev/skills/duvoai/cua-mcp-server/cua-cloud"><img src="https://agentmods.dev/badge/skills/duvoai/cua-mcp-server/cua-cloud/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/duvoai/cua-mcp-server/cua-cloud"><img src="https://agentmods.dev/badge/skills/duvoai/cua-mcp-server/cua-cloud.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,160 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown 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	$0.00090	$0.02160
Opus 5.5	$0.00036	$0.00864
Sonnet 5.5	$0.00018	$0.00432
Haiku 4.5	$0.00009	$0.00216

Measured 2mo ago against content hash 2902f07e5be2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

cua-cloud scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://cua.ai/cli/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LsSf https://cua.ai/cli/install.sh | sh

.claude/skills/cua-cloud/SKILL.md · 329 lines

The source is not reproduced here

No licence file

Read it on GitHub

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.

2mo ago First seen · 329 lines · 90 tokens per session scan C 2902f07e5be2

Subscribe to this mod's changes

cua-cloud is a skill published in the GitHub repository duvoai/cua-mcp-server (2 stars, last pushed 10mo ago), with no licence file. It adds 90 tokens to every session and 2,160 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

cua-cloud next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cua-cloudduvoai/cua-mcp-server	Skill	2	10mo ago	none	C	90	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code

cua-mcp-server: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codehighSupply chain

Makes network callslowCapability

The source is not reproduced here

No licence file

What this file has done since we first saw it

cua-cloud compared with skills from other repositories