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 aAAaqwq/AGI-Super-Team --skill automate-macos-cua-drivergit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/automate-macos-cua-driver)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/automate-macos-cua-driver"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/automate-macos-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/aaaaqwq/agi-super-team/automate-macos-cua-driver"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/automate-macos-cua-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00724 |
| Opus 5 | $0.00020 | $0.00362 |
| Sonnet 5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
automate-macos-cua-driver 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 7d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automate macOS with cua-driver
Treat cua-driver as a versioned transport with explicit capabilities. Keep AX perception, page-level evidence, foreground input, and business-state verification separate.
Workflow
- Pin the runtime contract. Record macOS, Chrome, cua-driver, packaged app, and target-site versions. Run driver health and tool-description checks; do not assume a capability from an older version.
- Establish permissions. Verify Accessibility and Screen Recording for the actual executable or signed app identity. Verify Chrome automation/page-bridge prerequisites only when the workflow needs them.
- Start one daemon. Prefer the packaged driver app when required for TCC identity. Pass only documented or deliberately version-pinned environment flags. Wait for readiness with a bounded probe.
- Own one session. Use a unique session name, close stale same-name sessions before starting, and register idempotent cleanup for normal exit, signals, exceptions, and timeouts.
- Find and activate the target window. Match application and window identity, reject hidden or invalid geometry, and foreground only immediately before actions that require it.
- Read fresh AX state. Locate elements by role, label, ancestry, and current frame. Treat element indexes as snapshot-local and reacquire after scrolling or navigation.
- Choose the correct action path. Use the page bridge for DOM-only identity or authenticated in-page fetches when supported. Use foreground driver mouse/keyboard delivery for visible business actions that must behave like user input.
- Verify the business result. Poll a new AX/page snapshot for the intended state transition. Driver success,
verified, or an accepted event is not enough. - Protect identity and files. Bind selected object, visible panel, action source, preview, downloaded file, hash, and persisted owner. Fail closed on disagreement.
- Recover cleanly. Close previews, clear draft input when appropriate, end the session, and confirm the driver did not hide or strand the browser window.
What ships with it
4 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.
- 7d ago First seen · 42 lines · 40 tokens per session scan A d59cbfff2d70
automate-macos-cua-driver is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (92 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 724 once invoked, about $0.0002 per session on Opus 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 2026-09-05.
Other skills, from other repositories
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
qa
QA testing skill with real browser automation. Use when asked to "test this site", "QA this page", "check for visual bugs", "verify the deploy", or when Hydra needs browser validation for UI changes. Requires the browse binary.
chrome-devtools
Drive the machine Chrome debug browser via OpenClaw-managed MCP (chrome-devtools). Use for page navigation, snapshots, screenshots, clicks, forms, console/network inspection — not for host shell risk.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
flo
MoFlo ticket spell - analyze and execute GitHub issues.
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.