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 sthamann/nyx-local-ai --skill nyx-ui-screenshotsgit clone --depth 1 https://github.com/sthamann/nyx-local-aiWrote 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/sthamann/nyx-local-ai/nyx-ui-screenshots)<a href="https://agentmods.dev/skills/sthamann/nyx-local-ai/nyx-ui-screenshots"><img src="https://agentmods.dev/badge/skills/sthamann/nyx-local-ai/nyx-ui-screenshots/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/sthamann/nyx-local-ai/nyx-ui-screenshots"><img src="https://agentmods.dev/badge/skills/sthamann/nyx-local-ai/nyx-ui-screenshots.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 | $0.00064 | $0.00513 |
| Opus 5 | $0.00032 | $0.00257 |
| Sonnet 5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
nyx-ui-screenshots 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.
What it actually says
Regenerating the UI screenshots
The README images in docs/ are captured from .harness/index.html, which
renders the real webview bundle (media/main.js + main.css) with scripted
demo data inside a 430px sidebar frame.
Workflow
- Build the current bundle:
npm run build - Serve the repo (background):
python3 -m http.server 8321 --bind 127.0.0.1 - Capture each scene with the IDE browser at
http://127.0.0.1:8321/.harness/index.html?scene=<scene>; wait until the page title readsnyx-scene-<scene>-ready, then take a screenshot.
| Scene | Target file | Shows |
|---|---|---|
chat |
docs/nyx-agent-run.png |
tool cards, diff card, answer, 1M context meter |
approval |
docs/nyx-approval.png |
diff-preview approval, Always allow, queue |
machines |
docs/nyx-machines.png |
machine manager (DGX / Mac Studio) |
- Center-crop each capture to the frame (screenshots are centered):
sips -c 1839 1062 docs/<file>.png --out docs/<file>.png
(Values assume the default 714×1024 CSS viewport at ~2.22× scale — if the frame looks cut off, recompute: crop ≈ (430+68)×(780+68) CSS px × scale.)
- Review the images (read the files) before committing: no debug text, context meter plausible, no real secrets/IPs you don't want public.
Editing the scenes
Demo data lives in .harness/index.html (sceneChat, sceneApproval,
sceneMachines) — plain HostToWebview messages. When new UI features ship,
extend the relevant scene so the screenshots keep showcasing them.
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 · 43 lines · 64 tokens per session scan A 2ffd8522088f
nyx-ui-screenshots is a skill published in the GitHub repository sthamann/nyx-local-ai (137 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 513 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
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.
dev-browser
Control a local or remote browser with sandboxed JavaScript scripts. Uses a QuickJS WASM sandbox (not Node.js) with a pre-connected browser global and full Playwright Page API. Backed by a persistent daemon that manages named browser instances between script runs. Use for UI testing, web scraping, and automation where…
browserbase-ui-test
Adversarial UI testing via browser automation — tries to BREAK the app, not confirm it works. Analyzes git diffs to test changed code, or explores the full app for defects. Use before merging UI changes or to audit the deployed platform.
verify
How to run and drive this app to verify UI/server changes at runtime.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
test-ui
Test the Wayfinder agent extension UI by starting the dev environment and visually verifying changes via CDP. Covers the new tab page (left sidebar — Home, Scheduled Tasks, Settings, etc.) and the right side panel (chat interface). Use after making UI changes to apps/agent/.