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 asattelmaier/gnome-ui-mcp --skill gnome-ui-testinggit clone --depth 1 https://github.com/asattelmaier/gnome-ui-mcpWrote 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/asattelmaier/gnome-ui-mcp/gnome-ui-testing)<a href="https://agentmods.dev/skills/asattelmaier/gnome-ui-mcp/gnome-ui-testing"><img src="https://agentmods.dev/badge/skills/asattelmaier/gnome-ui-mcp/gnome-ui-testing/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/asattelmaier/gnome-ui-mcp/gnome-ui-testing"><img src="https://agentmods.dev/badge/skills/asattelmaier/gnome-ui-mcp/gnome-ui-testing.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 | $0.00041 | $0.00507 |
| Opus 5 | $0.00020 | $0.00253 |
| Sonnet 5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
gnome-ui-testing 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 10d 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.
What it actually says
Core Concepts
State snapshots: snapshot_state captures the full desktop state (applications, windows, focus, popups). compare_state diffs two snapshots to detect changes. Use these to verify side effects of actions.
Assertions: assert_element and assert_text poll for conditions with a timeout, making them suitable for async UI that takes time to settle.
Visual verification: screenshot + visual_diff for pixel-level comparison. get_pixel_color and get_region_color for spot checks.
Workflow Patterns
Verifying an action took effect
snapshot_statebefore the action- Perform the action (click, type, etc.)
snapshot_stateafter the actioncompare_statethe two snapshots to see what changed
Waiting for UI to settle
wait_for_element(query="Save completed")waits for an element to appearwait_for_element_gone(query="Loading...")waits for an element to disappearwait_for_shell_settledwaits for GNOME Shell animations to finishwait_for_popup_countwaits for a specific number of popups
Asserting element state
assert_element(query="Submit", role="push button", expected_states=["sensitive"])
This polls until the Submit button exists and is sensitive (enabled), or times out.
Visual regression testing
screenshot(filename="baseline.png")for the reference image- Perform the action
screenshot(filename="current.png")visual_diff(image_path_1="baseline.png", image_path_2="current.png")
OCR-based verification
ocr_screenextracts all visible text from the screenfind_text_ocrlocates specific text by position- Useful when AT-SPI does not expose the text (e.g. rendered images)
Best Practices
- Always use timeouts on wait/assert tools to avoid hanging
- Prefer
assert_elementover manual find + check loops - Use
showing_only=Trueto ignore hidden elements - Take screenshots at key checkpoints for debugging failed tests
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.
- 10d ago First seen · 57 lines · 41 tokens per session scan A bfaf1cc0ae87
gnome-ui-testing is a skill published in the GitHub repository asattelmaier/gnome-ui-mcp (1 stars, last pushed 26d ago), licensed MIT. It adds 41 tokens to every session and 507 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 2026-08-31.
Other skills, from other repositories
tauri-pilot
Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
web-navigator
A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.
computer-use
Linux/X11 desktop control — inspect, click, type into visible windows via AT-SPI + xdotool. Returns @eN refs from the focused window's accessibility tree.
qa-smoke-test
Run automated QA tests on desktop apps or websites. Smoke tests, visual regression, UI validation, accessibility checks, end-to-end flows. Use when: "test this app", "smoke test", "check if login works", "validate the UI", "visual regression", "verify button is clickable", "test flow", "QA check", "accessibility…
agent-desktop
Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 59 command…