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.
Borrowing it
Nothing to install: this file belongs to trycua/cua. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/trycua/cua/main/.cursor/skills/verify-cua-spaces/SKILL.mdgit 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/verify-cua-spaces)<a href="https://agentmods.dev/skills/trycua/cua/verify-cua-spaces"><img src="https://agentmods.dev/badge/skills/trycua/cua/verify-cua-spaces/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/verify-cua-spaces"><img src="https://agentmods.dev/badge/skills/trycua/cua/verify-cua-spaces.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 | $0.00097 | $0.02122 |
| Opus 5.5 | $0.00039 | $0.00849 |
| Sonnet 5.5 | $0.00019 | $0.00424 |
| Haiku 4.5 | $0.00010 | $0.00212 |
Grade A, and why
verify-cua-spaces scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Run from the repository root. Linux only. Needs Rust (pinned by the workspaces), `protoc`, Node 20+, Chromium, `Xvfb`, `openbox`, `dbus-daemon`, `curl`, `ss`, `python3`, and for audio `pipewire`, `wireplumber`, `pipewire How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Cua Spaces
A Space is any machine running cua-spacesd (port 3211 in an image; a random loopback port here). Users reach it through the cua CLI (cua spaces, cua sb view, cua do, cua spacesd, cua mcp), the HTML5 viewer that cua-spacesd serves at /viewer/, and the desktop apps (Tauri, Electron, SwiftUI) that sit on the same SDK. This skill drives the CLI and the viewer against a throwaway Linux desktop. Read the feature map before picking a journey.
Everything here is source-built: libs/cua-spacesd (the daemon and the cua-spacesd-x11-pad input-echo fixture) and libs/cua (cua-spaces-cli, the Spaces build of cua; the apps ship it as cua). Never drive a cua-spacesd, cua daemon or ~/.cua you did not start: every run gets its own display, session bus, audio server, port, token and cua home.
Launch
Run from the repository root. Linux only. Needs Rust (pinned by the workspaces), protoc, Node 20+, Chromium, Xvfb, openbox, dbus-daemon, curl, ss, python3, and for audio pipewire, wireplumber, pipewire-pulse (Debian/Ubuntu: the build packages in .github/workflows/ci-cua-spacesd.yml plus xvfb openbox dbus chromium pipewire wireplumber pipewire-pulse pulseaudio-utils).
H=.cursor/skills/verify-cua-spaces/scripts/spaces-desk.sh
$H build # once: release cua-spacesd, cua-spacesd-x11-pad, cua-spaces-cli (~20 min cold, ~9 GB of target/)
$H up # or: $H up --no-audio
up starts, in this order and each in its own session: Xvfb on a free display (1280x800), a private D-Bus session bus, PipeWire + WirePlumber + pipewire-pulse (skipped with --no-audio or when not installed), openbox, the x11-pad fixture filling the screen with a red/green/blue/white grid, and cua-spacesd on a free loopback port with a fresh token and data dir (--quic-port 0). It then registers the Space with cua spaces add 127.0.0.1:<port> --name verify in an isolated CUA_HOME.
What ships with it
8 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.
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.
- 2d ago First seen · 85 lines · 97 tokens per session scan A 2800e9f7e5f7
verify-cua-spaces is a skill published in the GitHub repository trycua/cua (31,822 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 2,122 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-04.
verify-cua-spaces compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| verify-cua-spacestrycua/cua | Skill | 32k | today | MIT | A | 97 | Cursor |
| walkthroughjoshukraine/dotfiles | Skill | 429 | 10d ago | MIT | A | 33 | Claude Code |
| webapp-testingKUP-IP/the-bridge | Skill | 9 | 1mo ago | none | A | 35 | Claude Code, Codex |
| playwright-cliIvanCampos/agents | Skill | 5 | 8mo ago | MIT | A | 74 | Codex |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| create-verification-skillget-bb/bb | Skill | 4.9k | today | MIT | A | 57 | Claude Code, Codex |
| browser-qahashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |