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.svg" alt="Measured on agentmods" 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 | $0.00567 |
| Opus 5 | $0.00044 | $0.00283 |
| Sonnet 5 | $0.00017 | $0.00113 |
| Haiku 4.5 | $0.00009 | $0.00057 |
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 yesterday.
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
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). Background it and note the port (default 4327). - 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.
Why not mockups
A mockup gets one reaction ("looks fine") and then the work is thrown away. The real build gets the same reaction plus every real bug found before the feature ships. The mockup path only wastes the turn it saves.
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.
- yesterday First seen · 45 lines · 87 tokens per session scan A 607e9d142ffc
aster-ui-demo is a skill published in the GitHub repository Zfinix/aster (46 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 567 once invoked, about $0.0004 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 2026-09-06.
Other skills, from other repositories
figma-to-webui
Recreate Figma design frames as production-ready Chromium WebUI code following Chrome's Lit-element architecture and styling guidelines. Use when asked to create WebUI code from a Figma frame URL.
generate-token-map
Maps all Figma design tokens from figma-variables.md to their equivalent C++ (Views) identifiers, CSS (WebUI) variables, and Clank (Android) resource attributes/macros/methods in Chromium, and saves the formatted mapping table to the assets directory of the Chrome Design System project. Use this skill when asked to…
Webdesign
Design and integrate web interfaces via three paths: DirectDesign (write design inline with Anthropic frontend-design philosophy — the default workhorse), native /design + /design-sync Claude Code commands (preferred for code integration and design-system sync), or ClaudeDesign (drive claude.ai/design through…
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
memstack-security-csp-headers
Use this skill when the user says 'CSP', 'Content-Security-Policy', 'security headers', 'HSTS', 'X-Frame-Options', 'clickjacking', 'unsafe-inline', 'unsafe-eval', or needs to audit, generate, or fix HTTP security headers for a web application. Do NOT use for API route audits or dependency scanning.
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.