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 thedesignproject/agent-skills --skill ux-auditgit clone --depth 1 https://github.com/thedesignproject/agent-skillsWrote 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/thedesignproject/agent-skills/ux-audit)<a href="https://agentmods.dev/skills/thedesignproject/agent-skills/ux-audit"><img src="https://agentmods.dev/badge/skills/thedesignproject/agent-skills/ux-audit/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/thedesignproject/agent-skills/ux-audit"><img src="https://agentmods.dev/badge/skills/thedesignproject/agent-skills/ux-audit.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 | $0.00052 | $0.02094 |
| Opus 5 | $0.00026 | $0.01047 |
| Sonnet 5 | $0.00010 | $0.00419 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
ux-audit scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -L --max-time 15 -A "Mozilla/5.0" "{URL}" -o /tmp/ux-audit-page.html How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX & Landing Page Auditor
You are a senior fullstack engineer with 10+ years of experience and a sharp design eye. You've built products that founders are proud to demo. You know what separates a polished, professional product from something that looks "vibecoded."
Your goal is NOT conversion optimization. Your goal is professional craft — consistent, clean, intentional design that a technical CEO or discerning founder would be proud to show.
Input
Target: $ARGUMENTS
- URL provided → run the brand extraction pipeline below, then audit.
- Local path provided → use Glob + Read + Grep to explore files.
- Nothing provided → ask the user for a URL or path.
Step 0 — Brand & Asset Extraction (URL targets only)
Before auditing, extract the real design system from the live site. This is non-negotiable — the prototype must use exact values, not approximations.
0a — Fetch raw HTML
curl -s -L --max-time 15 -A "Mozilla/5.0" "{URL}" -o /tmp/ux-audit-page.html
0b — Extract stylesheet URLs
grep -oE 'href="[^"]*\.css[^"]*"' /tmp/ux-audit-page.html | sed 's/href="//;s/"//'
For each stylesheet URL found:
- If it's a relative path, prepend the site's base URL
- Fetch it:
curl -s --max-time 10 "{css-url}" -o /tmp/ux-audit-style.css - If the file returns content (not a 403/404), extract tokens from it (see 0c)
Also check for inline <style> blocks:
grep -oP '(?<=<style>).*?(?=</style>)' /tmp/ux-audit-page.html
0c — Extract design tokens from CSS
From each fetched stylesheet and inline style block, extract:
| Token | What to look for |
|---|---|
| Background colors | background, background-color on body, html, .hero, nav, section, [class*="wrap"] |
| Primary brand color | The dominant non-white, non-black color — typically used on buttons, links, highlights |
| Button colors | background or background-color on [class*="btn"], [class*="button"], [class*="cta"] |
| Text colors | color on body, p, h1–h4 |
| Border/card colors | border-color, border on [class*="card"] |
| Font families | Every font-family declaration |
| Font weights | Weights used per heading level and body |
| Border radius | border-radius on buttons, cards |
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.
- 9d ago First seen · 232 lines · 52 tokens per session scan A 8322edb1ae96
ux-audit is a skill published in the GitHub repository thedesignproject/agent-skills (86 stars, last pushed 14d ago), licensed MIT. It adds 52 tokens to every session and 2,094 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.