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 YuqingNicole/variant-design-skill --skill variant-design-systemgit clone --depth 1 https://github.com/YuqingNicole/variant-design-skillWrote 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/yuqingnicole/variant-design-skill/variant-design-system)<a href="https://agentmods.dev/skills/yuqingnicole/variant-design-skill/variant-design-system"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-design-system/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/yuqingnicole/variant-design-skill/variant-design-system"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-design-system.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 | $0.00074 | $0.04148 |
| Opus 5 | $0.00037 | $0.02074 |
| Sonnet 5 | $0.00015 | $0.00830 |
| Haiku 4.5 | $0.00007 | $0.00415 |
Grade A, and why
variant-design-system 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 10d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before generating code, load
skills/shared/code-output.mdfor framework detection and output conventions.
Design System Mode
The canonical workflow for production-quality work. Define once, generate consistently.
ds → confirm → component [name] → compose [page]
↑ ↑ ↑
Token foundation Atomic pieces Assembled layouts
Triggers
| User says | Action |
|---|---|
ds / "create a design system" / "define tokens" / "set up tokens" |
Generate design system → preview → confirm |
ds confirm |
Lock current design system as constraint for all future outputs |
ds edit [section] |
Edit one section of the design system (palette / type / spacing / motion) without regenerating all |
ds show |
Print current design system token summary in terminal |
component [name] (after DS confirmed) |
Generate component using locked DS tokens, all 8 states |
compose [page name] |
Assemble confirmed components into a page, 3 layout variations |
compose [page] using A B C |
Compose page from specific named components |
Step 1 — Generate Design System (ds)
Before generating, ask 3 focused questions (can be answered in one message):
- Brand personality — 2–3 adjectives that describe the feel (e.g. "precise, warm, understated")
- Color direction — existing brand color, or a reference (hex / site URL / mood word)
- Typeface preference — existing fonts, or a direction ("editorial serif", "clean geometric sans", "monospace-forward")
If user says "surprise me" or has no preferences, infer from their codebase (README, existing CSS, component names) or pick a strongly opinionated direction and state it.
Generate variant-output/design-system.css — a complete, self-documenting token file:
/* ═══════════════════════════════════════════════════
DESIGN SYSTEM — [Project Name]
Generated by variant-design · [date]
Confirm with: ds confirm
Edit with: ds edit [palette | type | spacing | motion | elevation | radius]
═══════════════════════════════════════════════════ */
/* ── Primitives ─────────────────────────────────── */
:root {
/* Color primitives — OKLCH */
--p-brand-50: oklch(97% 0.02 [H]);
--p-brand-100: oklch(93% 0.04 [H]);
--p-brand-200: oklch(86% 0.08 [H]);
--p-brand-300: oklch(76% 0.13 [H]);
--p-brand-400: oklch(66% 0.18 [H]);
--p-brand-500: oklch(56% 0.20 [H]); /* primary */
--p-brand-600: oklch(46% 0.18 [H]);
--p-brand-700: oklch(36% 0.15 [H]);
--p-brand-800: oklch(26% 0.10 [H]);
--p-brand-900: oklch(16% 0.06 [H]);
--p-neutral-50: oklch(98% 0.005 [H]);
--p-neutral-100: oklch(95% 0.008 [H]);
--p-neutral-200: oklch(90% 0.010 [H]);
--p-neutral-300: oklch(82% 0.012 [H]);
--p-neutral-400: oklch(68% 0.010 [H]);
--p-neutral-500: oklch(55% 0.008 [H]);
--p-neutral-600: oklch(42% 0.008 [H]);
--p-neutral-700: oklch(30% 0.006 [H]);
--p-neutral-800: oklch(20% 0.005 [H]);
--p-neutral-900: oklch(12% 0.004 [H]);
--p-success: oklch(55% 0.18 145);
--p-warning: oklch(60% 0.18 80);
--p-error: oklch(55% 0.22 25);
--p-info: oklch(55% 0.18 250);
}
/* ── Semantic tokens ─────────────────────────────── */
:root {
/* Surfaces */
--color-bg: var(--p-neutral-50);
--color-surface: #ffffff;
--color-surface-2: var(--p-neutral-100);
--color-surface-3: var(--p-neutral-200);
/* Borders */
--color-border: var(--p-neutral-200);
--color-border-strong: var(--p-neutral-300);
/* Text */
--color-text-primary: var(--p-neutral-900);
--color-text-secondary: var(--p-neutral-600);
--color-text-tertiary: var(--p-neutral-400);
--color-text-on-accent: #ffffff;
/* Brand */
--color-accent: var(--p-brand-500);
--color-accent-hover: var(--p-brand-600);
--color-accent-subtle: var(--p-brand-50);
--color-accent-border: var(--p-brand-200);
/* Semantic */
--color-success: var(--p-success);
--color-success-subtle: oklch(97% 0.03 145);
--color-warning: var(--p-warning);
--color-warning-subtle: oklch(98% 0.03 80);
--color-error: var(--p-error);
--color-error-subtle: oklch(97% 0.03 25);
}
/* ── Typography ─────────────────────────────────── */
:root {
--font-display: '[Display Font]', serif; /* or sans-serif */
--font-body: '[Body Font]', sans-serif;
--font-mono: 'IBM Plex Mono', monospace;
/* Scale — ratio [ratio] */
--text-xs: clamp(0.69rem, 0.65rem + 0.2vw, 0.75rem);
--text-sm: clamp(0.8rem, 0.77rem + 0.2vw, 0.875rem);
--text-base: clamp(0.95rem, 0.9rem + 0.25vw, 1.0625rem);
--text-lg: clamp(1.1rem, 1rem + 0.5vw, 1.25rem);
--text-xl: clamp(1.3rem, 1.1rem + 1vw, 1.75rem);
--text-2xl: clamp(1.6rem, 1.2rem + 2vw, 2.5rem);
--text-3xl: clamp(2rem, 1.4rem + 3vw, 3.5rem);
--text-4xl: clamp(2.5rem, 1.6rem + 5vw, 5.5rem);
/* Weights */
--font-weight-normal: 400;
--font-weight-medium: 500;
--font-weight-semibold: 600;
--font-weight-bold: 700;
/* Line heights */
--leading-tight: 1.2;
--leading-snug: 1.35;
--leading-normal: 1.5;
--leading-relaxed: 1.7;
/* Tracking */
--tracking-tight: -0.04em;
--tracking-snug: -0.02em;
--tracking-normal: 0;
--tracking-wide: 0.04em;
--tracking-caps: 0.08em;
}
/* ── Spacing ─────────────────────────────────────── */
:root {
/* 4pt base grid */
--space-1: 4px;
--space-2: 8px;
--space-3: 12px;
--space-4: 16px;
--space-5: 20px;
--space-6: 24px;
--space-8: 32px;
--space-10: 40px;
--space-12: 48px;
--space-16: 64px;
--space-20: 80px;
--space-24: 96px;
/* Layout */
--container-sm: 640px;
--container-md: 768px;
--container-lg: 1024px;
--container-xl: 1280px;
--container-2xl: 1440px;
}
/* ── Radius ──────────────────────────────────────── */
:root {
--radius-xs: 2px;
--radius-sm: 4px;
--radius-md: 6px;
--radius-lg: 10px;
--radius-xl: 16px;
--radius-2xl: 24px;
--radius-full: 9999px;
}
/* ── Elevation (shadow) ──────────────────────────── */
:root {
--shadow-xs: 0 1px 2px rgba(0,0,0,0.05);
--shadow-sm: 0 1px 4px rgba(0,0,0,0.07), 0 0 0 1px rgba(0,0,0,0.04);
--shadow-md: 0 4px 12px rgba(0,0,0,0.08), 0 0 0 1px rgba(0,0,0,0.04);
--shadow-lg: 0 8px 24px rgba(0,0,0,0.10), 0 0 0 1px rgba(0,0,0,0.04);
--shadow-xl: 0 16px 48px rgba(0,0,0,0.12), 0 0 0 1px rgba(0,0,0,0.05);
/* Focus ring */
--ring-width: 2px;
--ring-offset: 2px;
--ring-color: var(--color-accent);
}
/* ── Motion ──────────────────────────────────────── */
:root {
/* Durations */
--duration-instant: 80ms;
--duration-fast: 150ms;
--duration-normal: 250ms;
--duration-slow: 400ms;
--duration-slower: 600ms;
/* Easings */
--ease-out: cubic-bezier(0.0, 0.0, 0.2, 1);
--ease-in: cubic-bezier(0.4, 0.0, 1, 1);
--ease-in-out: cubic-bezier(0.4, 0.0, 0.2, 1);
--ease-out-expo: cubic-bezier(0.16, 1, 0.3, 1);
--ease-spring: cubic-bezier(0.175, 0.885, 0.32, 1.275);
/* Common transitions */
--transition-fast: all var(--duration-fast) var(--ease-out);
--transition-normal: all var(--duration-normal) var(--ease-out);
--transition-colors: color var(--duration-fast) var(--ease-out),
background-color var(--duration-fast) var(--ease-out),
border-color var(--duration-fast) var(--ease-out);
}
/* ── Z-index ─────────────────────────────────────── */
:root {
--z-base: 0;
--z-raised: 10;
--z-dropdown: 100;
--z-sticky: 200;
--z-overlay: 300;
--z-modal: 400;
--z-toast: 500;
}
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.
- 10d ago First seen · 385 lines · 0 tokens per session scan A 98863a2d3f4e
variant-design-system is a skill published in the GitHub repository YuqingNicole/variant-design-skill (46 stars, last pushed 28d ago), licensed MIT. It adds 74 tokens to every session and 4,148 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
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
industrial-brutalist-ui
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.