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 Zfinix/aster --skill aster-ui-demogit clone --depth 1 https://github.com/Zfinix/asterWrote 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/zfinix/aster/aster-ui-demo)<a href="https://agentmods.dev/skills/zfinix/aster/aster-ui-demo"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-ui-demo/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/zfinix/aster/aster-ui-demo"><img src="https://agentmods.dev/badge/skills/zfinix/aster/aster-ui-demo.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 | $0.00087 | $0.00668 |
| Opus 5.5 | $0.00035 | $0.00267 |
| Sonnet 5.5 | $0.00017 | $0.00134 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
aster-ui-demo 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo UI work in the real surface
Never build a standalone HTML mockup to show a UI idea. Users judge UI by clicking the real product, and a mockup cannot answer the only questions that matter: does it work, does it match the surrounding design, does it survive real data.
The workflow
-
Build it for real. Implement the change in the actual frontend source, even when the user only asked to "see it first". For this repo that means
editors/vscode/webview/(shared webview used by both the VS Code panel and the browser harness) ordesktop/for Tauri surfaces. -
Serve it in the browser harness. From
editors/vscode/, runbun run dev:web(builds the webview, then runsout/devhost/main.js, a real browser-runnable host with a stubbedvscodeAPI). The devhost is a long-lived server: never run it directly throughrun_command, or the tool hangs until the process is killed. Fire and forget through a shell:bash -lc "cd editors/vscode && bun run dev:web > /tmp/devhost.log 2>&1 &"Note the port (default 4327). If the port does not come up, read
/tmp/devhost.login a later round instead of chaining a wait onto the start command. -
Click through it yourself first. Use browser automation to exercise the feature before the user sees it: open the panel, trigger the feature, resize narrow (300px) to check layout. Fix what breaks.
-
Open it for the user. Use
open_previewon the harness URL so they can click through the running app. State plainly that it is the real surface, running in a browser host. -
Run the real checks before calling it done:
bun run test(vitest) ineditors/vscode/, andmake checkor scopedcargo test -p aster-clifor Rust changes.
Reporting
Reference real files with line numbers, describe behavior the user can trigger by clicking, and note anything the browser harness cannot reproduce (native menus, real extension API calls) so the user knows what still needs testing in the actual editor.
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.
- 1mo ago Changed · +9 lines 866ca30cc3ac
- 1mo ago First seen · 45 lines · 87 tokens per session scan A 607e9d142ffc
aster-ui-demo is a skill published in the GitHub repository Zfinix/aster (132 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 668 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
metis-browser
Control Metis Desktop Inspector built-in browser for local preview (HTML/SVG/file paths), page interaction, accessibility snapshots, and screenshots. Use when the user asks to open, show, preview, inspect, click, type, or verify UI in the in-app/built-in browser. Prefer browsernavigate over bash…
Interceptor
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…
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.
responsiveness-check
Test website responsiveness across viewport widths using browser automation. Resizes a single session through breakpoints, screenshots each width, and detects layout transitions (column changes, nav switches, overflow). Produces comparison reports showing exactly where layouts break. Trigger with 'responsiveness…
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.