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-driver/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-driver)<a href="https://agentmods.dev/skills/trycua/cua/verify-cua-driver"><img src="https://agentmods.dev/badge/skills/trycua/cua/verify-cua-driver/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-driver"><img src="https://agentmods.dev/badge/skills/trycua/cua/verify-cua-driver.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 | $0.00060 | $0.02644 |
| Opus 5.5 | $0.00024 | $0.01058 |
| Sonnet 5.5 | $0.00012 | $0.00529 |
| Haiku 4.5 | $0.00006 | $0.00264 |
Grade B, and why
verify-cua-driver scanned grade B 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get update How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Cua Driver
Read the feature map first. This verifies the daemon's desktop-tool surface, not the bench, and does not certify every mapped entry point by exercising one convenient path. Use only a disposable desktop: the foreground cells intentionally move focus and input.
Pick the lane
| Change touches | Lane | Entry point |
|---|---|---|
| Linux platform code, shared core/contract/SDK, this skill | Linux X11, plus Wayland for capture/input routes | scripts/verify-linux.sh x11|wayland (below) |
platform-macos, AppKit/SwiftUI/TextEdit harnesses, scripts/ci/macos/**, tests/runners/macos-lume/** |
macOS Lume guest | scripts/verify-macos.sh (macOS lane) |
| Shared code with macOS behavior | both | both |
Run every lane the change touches that the host can run, and name the lanes you skip in the report. Launch through Cleanup below cover Linux. The macOS lane keeps the same proof standards; its wrapper owns the worker VM, preflight and evidence collection.
Launch
Run from the repository root. Use the CI toolchain (Rust 1.97.1, Node 22) and install the Linux dependencies from .github/workflows/e2e-rust-linux.yml:
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
xvfb dbus-x11 at-spi2-core openbox picom python3-gi gir1.2-gtk-3.0 \
libgtk-3-dev clang pkg-config libdbus-1-dev libpipewire-0.3-dev \
libspa-0.2-dev libei-dev libx11-dev libxi-dev libxtst-dev libxext-dev \
libwebkit2gtk-4.1-dev libssl-dev libxdo-dev \
libayatana-appindicator3-dev librsvg2-dev ffmpeg jq x11-utils
CUA_E2E_RETRY_ONCE=0 .cursor/skills/verify-cua-driver/scripts/verify-linux.sh x11
The helper prints an absolute Evidence: directory under artifacts/cua-driver/verify/run-XXXXXXXX. Each invocation creates a new directory; never reuse an older canonical artifact directory. The canonical runner builds the release driver once and stages only Electron using tests/fixtures/build/linux.sh --only electron. Reuse that build with:
What ships with it
11 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.
- execution.md 3.3 KB
- features/background-input.md 2.5 KB
- features/click.md 2.5 KB
- features/README.md 2.0 KB
- features/scroll.md 2.0 KB
- features/type-text.md 2.2 KB
- features/window-discovery.md 2.0 KB
- macos-lume.md 5.6 KB
- scripts/check-evidence.sh 3.2 KB runs code
- scripts/verify-linux.sh 2.0 KB runs code
- scripts/verify-macos.sh 1.9 KB runs code
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.
- yesterday Changed · +17 lines · +19 tokens per session 4c1baf5f461c
- 13d ago First seen · 109 lines · 41 tokens per session scan B 993f6df51461
verify-cua-driver is a skill published in the GitHub repository trycua/cua (31,822 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 2,644 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-25.
verify-cua-driver compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| verify-cua-drivertrycua/cua | Skill | 32k | today | MIT | B | 60 | Cursor |
| jetson-video-pipelineNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 45 | Claude Code, Codex |
| asc-shots-pipelinerorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 79 | Claude Code |
| verify-ui-change-in-cloudwarpdotdev/warp | Skill | 66k | today | AGPL-3.0 | A | 69 | Claude Code |
| test-warp-uiwarpdotdev/warp | Skill | 66k | today | AGPL-3.0 | A | 55 | Claude Code |
| screenshot-automationrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 52 | Claude Code |
| test-generatorrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 33 | Claude Code |