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 doublesq97-ui/su-webstyle-top12 --skill su-webstyle-top12git clone --depth 1 https://github.com/doublesq97-ui/su-webstyle-top12Wrote 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/doublesq97-ui/su-webstyle-top12/su-webstyle-top12)<a href="https://agentmods.dev/skills/doublesq97-ui/su-webstyle-top12/su-webstyle-top12"><img src="https://agentmods.dev/badge/skills/doublesq97-ui/su-webstyle-top12/su-webstyle-top12/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/doublesq97-ui/su-webstyle-top12/su-webstyle-top12"><img src="https://agentmods.dev/badge/skills/doublesq97-ui/su-webstyle-top12/su-webstyle-top12.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00080 | $0.02007 |
| Opus 5 | $0.00040 | $0.01004 |
| Sonnet 5 | $0.00016 | $0.00401 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade A, and why
su-webstyle-top12 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 11d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SU Webstyle Top 12
Stable catalog of 12 web styles for selection and implementation. This skill is a decision + craft layer: it freezes tokens, composition rules, and acceptance evidence so weak models do not invent “generic cards with a new palette.”
Floor, Not Ceiling
- Recipes define the minimum bar (tokens, anti-patterns, evidence).
- Agents may exceed recipes, combine styles, or invent layouts when the user or a stronger capability requires it.
- When defaulting, follow the floor. When user globals / stronger intent conflict, prefer those and state that in plain text.
Route the Deliverable First
Classify before picking a style:
| Path | When | Structure source | Style source |
|---|---|---|---|
website |
Full site, landing, multi-section marketing page | Recipe signatures + section recipes · hero by default | Full recipe |
artifact |
Single-purpose HTML/card/board/tool/report shell | Template + density · no-hero by default | Skin only from recipe |
user-layout |
User global / project layout preference exists | User layout (usually no marketing hero) | Skin only |
Layout variants: read references/layout-variants.md. Same style id supports hero and no-hero; structure follows deliverable, not a locked “reading app” IA.
User layout priority
If memory, CLAUDE.md, Know-me, or project conventions define a preferred layout:
- Keep that structure (chrome, columns, scroll model).
- Apply this skill as skin only.
- Disclose, e.g.
已按你的全局排版习惯交付，本 skill 只套了 [style] 皮肤（色/字/边框圆角/阴影）。
Do not force a marketing hero onto a user layout unless asked.
Skin scope
Skin = color tokens, type stack/scale (as fits), radius, border, shadow, optional icon stroke.
Skin does not force Signature Hero, 100svh marketing sections, or section recipes.
Route the Request Mode
| Mode | When | Action |
|---|---|---|
| Browse | “有哪些风格 / atlas / 让我看看” | List Core 12 compactly; offer board |
| Choose | User wants options then self-pick | Show menu/board; wait for id/number |
| Recommend | “推荐 / 不知道选哪个” | 2–3 candidates + tradeoffs; do not hard-pick unless asked |
| Auto | “你决定 / 专业一点 / 做落地页” without a named style | Silently pick one; return id + one-line fit |
| Apply | Style known or Auto done | Load one recipe → contract → implement → evidence |
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.
- 11d ago First seen · 175 lines · 80 tokens per session scan A 76dacab7eb26
su-webstyle-top12 is a skill published in the GitHub repository doublesq97-ui/su-webstyle-top12 (14 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,007 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 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
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.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.