trycua/cua is a toolkit for building and testing AI agents that operate computers by seeing screens, clicking controls, and typing across operating systems and virtual machines. It serves agent developers, benchmark authors, and teams generating training data for computer-use models. Catalogue add-ons provide ways to operate Cua drivers and related agent workflows.
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.
npx skills add trycua/cua --skill cua-sandboxesgit clone --depth 1 https://github.com/trycua/cuaWrote 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.
[](https://agentmods.dev/skills/trycua/cua/cua-sandboxes)<a href="https://agentmods.dev/skills/trycua/cua/cua-sandboxes"><img src="https://agentmods.dev/badge/skills/trycua/cua/cua-sandboxes/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.
<a href="https://agentmods.dev/skills/trycua/cua/cua-sandboxes"><img src="https://agentmods.dev/badge/skills/trycua/cua/cua-sandboxes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00098 | $0.01563 |
| Opus 5.5 | $0.00039 | $0.00625 |
| Sonnet 5.5 | $0.00020 | $0.00313 |
| Haiku 4.5 | $0.00010 | $0.00156 |
Grade A, and why
cua-sandboxes 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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cua sandboxes
A sandbox is a disposable computer: a container or VM on this machine or in
the Cua cloud. The cua CLI and the cua SDK (Python, TypeScript, Swift,
Kotlin, Rust) share one runtime and one list of sandboxes.
Before you start
cua --version # the Rust cua CLI
cua auth status # the cloud needs `cua auth login` (or CUA_CLIENT_ID/CUA_CLIENT_SECRET)
cua config get default.on # where sandboxes run without --on (local unless changed)
cua runtime doctor # local runtimes (containers, gVisor, QEMU, Lume); read-only
Local sandboxes need no account. Cloud sandboxes are metered: always delete them when done.
Create
cua sb create linux --name dev # local (default): a gVisor container
cua sb create linux --kind vm --name dev # local Linux VM (QEMU)
cua sb create macos --name mac # local macOS VM (Apple silicon, Lume)
cua sb create linux --on cloud --name dev # the Cua cloud
cua sb create ghcr.io/org/image:tag --name x # any OCI image, local or --on cloud
cua sb create --on direct:127.0.0.1:3211 --token TOKEN --name mine # an existing machine running cua-spacesd
--on is where (local, cloud, direct:<addr>), --kind what
(auto, container, vm), --runtime which engine (auto; local gvisor,
runc, qemu, lume; cloud gvisor, kubevirt). An impossible combination
fails with invalid placement and lists the valid values. Local
runtimes are set up on first use (cua runtime setup does it explicitly).
Omit --name for a generated name. cua sb ls prints each sandbox's ref
(local:dev, cloud:dev, direct:host:port); every NAME argument takes a
ref or a bare name that is unique across locations (--local / --cloud
narrow it). Add --json to any command for
machine-readable output. exec, shell, cp, screenshots and GUI control
go through cua-spacesd, so use an image that ships it (the linux alias
does). Plain images still get lifecycle, logs and port-forward.
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.
- 14d ago First seen · 140 lines · 98 tokens per session scan A 792be84be21c
cua-sandboxes is a skill published in the GitHub repository trycua/cua (29,871 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,563 once invoked, about $0.0004 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 2026-10-02.
Other skills, from other repositories
apple-container
Build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS using Apple's open-source container CLI, no Docker daemon required.
peekaboo
Use Peekaboo for macOS screenshots, Accessibility inspection, and background app/window/UI automation, including fallback computer use when the primary tool cannot handle an authorized task.
vellum-browser-use
Browse the web using assistant browser CLI commands.
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
macos-harness
Read and operate the apps on this Mac from the shell. Use it when a task needs an app's UI and no API, CLI or purpose-built tool can do it.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.