TurixAI/TuriX-CUA is an open-source computer-use agent that lets AI models observe and operate a desktop computer through actions such as interacting with applications. It is intended for personal and research use, including desktop automation and computer-use experiments. The catalogue entry is an OpenClaw skill package for running TuriX.
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 TurixAI/TuriX-CUA --skill openclaw_turix_skillgit clone --depth 1 https://github.com/TurixAI/TuriX-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/turixai/turix-cua/openclaw_turix_skill)<a href="https://agentmods.dev/skills/turixai/turix-cua/openclaw_turix_skill"><img src="https://agentmods.dev/badge/skills/turixai/turix-cua/openclaw_turix_skill/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/turixai/turix-cua/openclaw_turix_skill"><img src="https://agentmods.dev/badge/skills/turixai/turix-cua/openclaw_turix_skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 60 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00053 | $0.03296 |
| Opus 5 | $0.00026 | $0.01648 |
| Sonnet 5 | $0.00011 | $0.00659 |
| Haiku 4.5 | $0.00005 | $0.00330 |
Grade A, and why
turix-mac 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 12d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TuriX-Mac Skill
This skill allows Clawdbot to control the macOS desktop visually using the TuriX Computer Use Agent.
When to Use
- When asked to perform actions on the Mac desktop (e.g., "Open Spotify and play my liked songs").
- When navigating applications that lack command-line interfaces.
- For multi-step visual workflows (e.g., "Find the latest invoice in my email and upload it to the company portal").
- When you need the agent to plan, reason, and execute complex tasks autonomously.
Key Features
🤖 Multi-Model Architecture
TuriX uses a sophisticated multi-model system:
- Brain: Understands the task and generates step-by-step plans
- Actor: Executes precise UI actions based on visual understanding
- Planner: Coordinates high-level task decomposition (when
use_plan: true) - Memory: Maintains context across task steps
📋 Skills System
Skills are markdown playbooks that guide the agent for specific domains:
github-web-actions: GitHub navigation, repo search, starringbrowser-tasks: General web browser operations- Custom skills can be added to the
skills/directory
🔄 Resume Capability
The agent can resume interrupted tasks by setting a stable agent_id.
Running TuriX
Basic Task
skills/local/turix-mac/scripts/run_turix.sh "Open Chrome and go to github.com"
Resume Interrupted Task
skills/local/turix-mac/scripts/run_turix.sh --resume my-task-001
✅ Note:
run_turix.shupdatesexamples/config.jsonfor you (task, resume,use_plan,use_skills). If you want to keep a hand-edited config, skip passing a task and editexamples/config.jsondirectly.
Tips for Effective Tasks
✅ Good Examples:
- "Open Safari, go to google.com, search for 'TuriX AI', and click the first result"
- "Open System Settings, click on Dark Mode, then return to System Settings"
- "Open Finder, navigate to Documents, and create a new folder named 'Project X'"
❌ Avoid:
- Vague instructions: "Help me" or "Fix this"
- Impossible actions: "Delete all files"
- Tasks requiring system-level permissions without warning
What ships with it
2 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.
- 12d ago First seen · 421 lines · 53 tokens per session scan A 71548a078882
turix-mac is a skill published in the GitHub repository TurixAI/TuriX-CUA (3,159 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 3,296 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate…
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…