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 kensaurus/cursor-kenji --skill enhance-web-uigit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/enhance-web-ui)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/enhance-web-ui"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/enhance-web-ui.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 | $0.00065 | $0.05652 |
| Opus 5 | $0.00032 | $0.02826 |
| Sonnet 5 | $0.00013 | $0.01130 |
| Haiku 4.5 | $0.00006 | $0.00565 |
Grade A, and why
enhance-web-ui 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 4d 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surface router:
/uiux. You are here:enhance-web-ui. Native iOS/Android (SwiftUI / Compose, no web layer) is out of scope — use Apple HIG / Material directly.
Enhance Page UI
Degree of freedom: MIXED. Composition and tier judgment [HIGH freedom]; live read, DOM rects, three-viewport verify [LOW freedom — run exactly].
Turn an existing screen into a composed interface: calmer hierarchy, smarter content placement, expressive but purposeful motion, and artful transitions that support comprehension. This is not a "add more chips/cards/shadows" skill. It rearranges, subtracts, and stages information before adding decoration.
Vague-but-visceral user feedback ("clunky", "atrocious", "wasted space", "incoherent height") almost always points to a
Hidden Failure Modefrom §X below — start there, not at the surface decoration the user named.
If browser automation is used, first follow the
protocol-browser-anti-stallskill when present.
How to reason
- Recon — primitives, tokens, real data contracts
- Rank — primary / secondary / metadata / actions / ambient
- Compose — subtract → group → pin → stage before decorating
- Verify — 1440/1024/800 + two squints + rect uniformity
Worked example
Recon: learning app (tier A); stat tiles share a Tooltip wrapper; "0/10 today" appears three times. Rank: primary is the next lesson CTA; the count is metadata, not a third headline. Compose: patch Tooltip to
block w-full; drop two duplicate counts; no extra chips. Verify: tile widths match; category squint shows distinct hues; CTA still one brand-color target.
Self-critique before reporting
- Compose first — decoration was not the first edit
- Real data — no mocked status/count; primitive patched if the bug repeats
- Three viewports — no wrapped CTAs; dead slots collapse when empty
- Right owner — flow/IA →
enhance-web-ux; breakpoints-only →audit-responsive
Critical Rules
What ships with it
1 file 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.
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.
- 4d ago First seen · 466 lines · 65 tokens per session scan A f4c8a318d95d
enhance-web-ui is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 10d ago), licensed MIT. It adds 65 tokens to every session and 5,652 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 2026-09-03.
Other skills, from other repositories
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
accessibility-audit
Conduct accessibility audits against WCAG 2.2 guidelines. Evaluate pages, components, and flows for conformance at A, AA, and AAA levels. Identify issues, assess severity, provide code fixes, and generate audit reports. Covers automated testing, manual testing, keyboard navigation, screen reader compatibility, color…
Responsive Layout Reviewer
Reviews HTML/CSS or component code for responsive design issues across mobile, tablet, and desktop breakpoints.
design-to-component-translator
Converts Figma/design specifications into production-ready UI components with accurate spacing, typography, color tokens, responsive rules, and interaction states (hover, focus, disabled, active). Generates Tailwind/shadcn code with design system tokens mapping. Use when translating "Figma to code", "design specs to…
responsive-design-system
Implements responsive design systems with mobile-first breakpoints, container queries, fluid typography, and adaptive layouts using Tailwind CSS. Use when users request "responsive design", "mobile-first", "breakpoints", "fluid typography", or "adaptive layout".