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 wilgon456/Paseobility --skill paseo-cuagit clone --depth 1 https://github.com/wilgon456/PaseobilityWrote 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/wilgon456/paseobility/paseo-cua)<a href="https://agentmods.dev/skills/wilgon456/paseobility/paseo-cua"><img src="https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-cua/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/wilgon456/paseobility/paseo-cua"><img src="https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-cua.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 | $0.00110 | $0.01199 |
| Opus 5.5 | $0.00044 | $0.00480 |
| Sonnet 5.5 | $0.00022 | $0.00240 |
| Haiku 4.5 | $0.00011 | $0.00120 |
Grade A, and why
paseo-cua 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 today.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paseo Cua Driver
trycua Cua Driver controls native app windows on macOS, Windows, and Linux.
Web pages belong to paseo-browser. If a CLI, API, AppleScript/osascript, or
file edit reaches the same outcome more reliably, use that and say so.
Ego Lite companion mode
For a task spanning a web page and a native application, keep Ego responsible for page actions and task-space cleanup. Read references/ego-companion.md for the artifact and control handoff. Preserve Ego's space ID/Page label across native work; do not create another browser space, attach Cua browser tools to that Page, or use Cua to bypass Ego's human-control/permission stops. Verify the native result before returning to a fresh Ego page observation.
Preconditions
cua-driver --version— binary present. If missing, use a non-GUI route if one exists; otherwise give the install command from references/setup.md, and run it if the user asks.cua-driver permissions status— on macOS, Accessibility and Screen Recording must be granted by the human.cua-driver permissions grantopens the right Settings entries; ask the user to approve them. Never fake or bypass a grant.
Skip a separate readiness ritual: the first snapshot and action on the real target are the check. When something fails, see references/recovery.md.
Discover the contract
The installed binary is authoritative; tool names and arguments change between releases:
cua-driver list-tools,cua-driver describe <tool>— exact tools/arguments.cua-driver --help— management subcommands.cua-driver mcp-config --client <client>— prints an MCP snippet to merge into the client config; it registers nothing by itself.
Core loop
- Find the window (
list_windows) or launch the app (launch_app). get_window_statefor the accessibility tree plus screenshot; narrow it withquery/max_elementsfirst. Row[N]is acted on aselement_token<snapshot_id>:N(e.g."s0000002a:11", not"11");element_indexis not an input. Use pixel coordinates from the same snapshot only when the tree cannot reach the target.- Act:
click,type_text,press_key,set_value,invoke_menu,set_window_frame,scroll. Batch known actions withrun_steps(observe:{}returns what changed) orrun_scriptwhen the flow needs a loop or branch, if the installed schema advertises them. A new snapshot stales old tokens; re-read withsince:"latest"for a diff. - Verify the final result at checkpoints with a fresh read (
verify_stateor the tree). A tool reply alone is not proof. - Background delivery is the default. If it is refused or unverifiable,
inspect the current result before switching to
delivery_mode: "foreground"and mention the focus change. Never replay an uncertain save/send/submit automatically.
What ships with it
6 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.
- today Changed 5597b1569f99
- yesterday Changed · +2 lines a90ae631b85e
- 4d ago Changed · +11 lines 1b4f8d5449f6
- 8d ago Changed · +14 lines · +36 tokens per session 2850cf97148f
- 15d ago Changed · +1 lines d9057faf6422
- 1mo ago Changed · +2 lines f5cfcb55caca
- 1mo ago First seen · 63 lines · 74 tokens per session scan A 9a16d525aca8
paseo-cua is a skill published in the GitHub repository wilgon456/Paseobility (25 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 1,199 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 2026-09-22.
Other skills, from other repositories
paseo-skins
Safely browse, create, inspect, install, switch, verify, and remove themes for the Paseo desktop app. Use when a user asks an agent to change Paseo's background, build a theme from an image, apply a Paseo skin, list available themes, diagnose a theme, or restore Paseo's native appearance.
live-voice-agent
A voice-control rule for a gated Korean-and-English voice assistant. It defines which wake phrases start listening and how spoken replies must be formatted.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.