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 NVIDIA-Omniverse/ovui --skill omniverse-ui-inspectorgit clone --depth 1 https://github.com/NVIDIA-Omniverse/ovuiWrote 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/nvidia-omniverse/ovui/omniverse-ui-inspector)<a href="https://agentmods.dev/skills/nvidia-omniverse/ovui/omniverse-ui-inspector"><img src="https://agentmods.dev/badge/skills/nvidia-omniverse/ovui/omniverse-ui-inspector/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/nvidia-omniverse/ovui/omniverse-ui-inspector"><img src="https://agentmods.dev/badge/skills/nvidia-omniverse/ovui/omniverse-ui-inspector.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 | $0.00091 | $0.02102 |
| Opus 5.5 | $0.00036 | $0.00841 |
| Sonnet 5.5 | $0.00018 | $0.00420 |
| Haiku 4.5 | $0.00009 | $0.00210 |
Grade A, and why
omniverse-ui-inspector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ovui Inspector
Drive standalone ovui applications through the ovui-inspect FastAPI server.
Quick Start
The tracked skill root in this repository is skills/omniverse-ui-inspector. Refer to
it from any clone with the repo-relative path; do not bake in machine-specific
absolute paths.
Launch the app with the skill root on PYTHONPATH. Set OVUI_REPO (or any
equivalent variable) to the local checkout of the ovui repository:
PYTHONPATH="${OVUI_REPO}/skills/omniverse-ui-inspector:${PYTHONPATH:-}" \
python -m ovui_widgets.app.headless --width 1280 --height 720
For a windowed app, use:
PYTHONPATH="${OVUI_REPO}/skills/omniverse-ui-inspector:${PYTHONPATH:-}" \
python -m ovui_widgets.app
The app imports ovuiinspect during startup. Importing the module starts a
localhost FastAPI server in a background thread and the app drains inspector
input actions on the ovui frame loop.
When using Codex or another command runner, keep the app command alive as a managed long-running foreground session, or launch it with an explicit detached-process wrapper that records the exact PID. Do not run the app through a command invocation that has a default timeout and then continue sending inspector commands after that invocation exits. If the app process is killed by the runner, follow-up keyboard commands will fail with connection refused even though the key is supported.
Defaults:
- Host:
127.0.0.1 - Port:
9910 - Override with
OVUIINSPECT_HOSTandOVUIINSPECT_PORT - Application state and checkpoint endpoints disabled by default; enable them
for state-guided QA with
OVUIINSPECT_ENABLE_STATE=1 - Python execution endpoint disabled by default; enable with
OVUIINSPECT_ENABLE_EXECUTE=1
Interface Priority
skills/omniverse-ui-inspector/scripts/ovui-inspect <command>from the repo root is the preferred CLI.python skills/omniverse-ui-inspector/scripts/ovui-inspect.py <command>is equivalent.- Raw HTTP against
http://127.0.0.1:9910is for debugging.
What ships with it
15 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.
- ovuiinspect/__init__.py 54 KB runs code
- ovuiinspect/commands.py 2.1 KB runs code
- references/api-endpoints.md 7.7 KB
- references/application-commands.md 7.5 KB
- references/coordinate-system.md 815 B
- requirements.txt 93 B
- scripts/ovui-inspect 320 B
- scripts/ovui-inspect.py 13 KB runs code
- tests/test_application_commands.py 12 KB runs code
- tests/test_cli_prog.py 757 B runs code
- tests/test_drag_modifiers.py 1.2 KB runs code
- tests/test_modifier_codes.py 1.0 KB runs code
- tests/test_native_screenshot_capture.py 5.1 KB runs code
- tests/test_screenshot_capture.py 13 KB runs code
- tests/test_state_snapshot.py 4.4 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.
- 15d ago Changed · +12 lines f3f53f4b363f
- 1mo ago First seen · 179 lines · 91 tokens per session scan A 3b03cf148de7
omniverse-ui-inspector is a skill published in the GitHub repository NVIDIA-Omniverse/ovui (55 stars, last pushed 15d ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,102 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 2026-08-30.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…