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 opensesh/DESIGN-OPS --skill design-system-qualitygit clone --depth 1 https://github.com/opensesh/DESIGN-OPSWrote 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/opensesh/design-ops/design-system-quality)<a href="https://agentmods.dev/skills/opensesh/design-ops/design-system-quality"><img src="https://agentmods.dev/badge/skills/opensesh/design-ops/design-system-quality/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/opensesh/design-ops/design-system-quality"><img src="https://agentmods.dev/badge/skills/opensesh/design-ops/design-system-quality.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 | $0.00029 | $0.01737 |
| Opus 5 | $0.00015 | $0.00869 |
| Sonnet 5 | $0.00006 | $0.00347 |
| Haiku 4.5 | $0.00003 | $0.00174 |
Grade A, and why
design-system-quality 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Quality
Ensure code meets design system standards for consistency, accessibility, and brand compliance.
Purpose
This skill provides quality gates for UI code reviews, ensuring all frontend work adheres to established design system patterns, accessibility standards, and component conventions.
When to Activate
Use this skill when:
- Reviewing UI/frontend code
- Conducting PR reviews for components
- Checking design system compliance
- After any UI component work
Quality Dimensions
1. Design Token Compliance
Color Usage
CORRECT WRONG
var(--bg-primary) bg-white
var(--fg-secondary) text-gray-500
var(--border-primary) border-slate-200
bg-bg-primary (Tailwind mapped) #191919 (hardcoded)
Verification Command:
# Find hardcoded colors (should return empty)
grep -rE "#[0-9A-Fa-f]{3,6}|rgb\(|rgba\(" --include="*.tsx" --include="*.css" | grep -v "var(--"
# Find forbidden Tailwind classes
grep -rE "bg-white|bg-black|text-white|text-black" --include="*.tsx"
Token Categories
| Category | Usage | Example |
|---|---|---|
| Background | Surface colors | var(--bg-primary), var(--bg-secondary) |
| Foreground | Text colors | var(--fg-primary), var(--fg-secondary) |
| Border | Line/divider colors | var(--border-primary), var(--border-secondary) |
| Brand | Accent/CTA colors | var(--brand-primary) |
2. Component Patterns
Accessible Component Libraries
All interactive elements should use accessible component libraries:
// CORRECT - Using accessible components
import { Button, Input, Select } from 'react-aria-components';
// Or: Radix UI, Headless UI, etc.
// WRONG - Missing accessibility
<button onClick={...}> // May miss keyboard/screen reader support
<input type="text" /> // May miss ARIA support
Card Pattern
// Standard Card
<div className={cn(
"bg-bg-secondary",
"border border-border-secondary",
"rounded-xl",
"hover:bg-bg-secondary-hover",
"hover:border-border-primary",
"transition-colors duration-150"
)}>
// Wrong patterns
<div className="bg-white rounded-lg shadow"> // Hardcoded colors
<div className="bg-gray-100 border-2"> // Wrong tokens
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 · 312 lines · 29 tokens per session scan A 7d8c49213cfe
design-system-quality is a skill published in the GitHub repository opensesh/DESIGN-OPS (23 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,737 once invoked, about $0.0001 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-to-code-check
Check alignment between a specific design specification and its code implementation — a focused, single-component or single-screen comparison. Trigger when someone says: does this match the design, check implementation, design code alignment, what's different between the design and the build, spec check…
design-pipeline
A build-and-test workflow for turning Figma designs into shadcn/ui components, a reusable set of interface components for React-based projects. It checks the result in a real browser at three screen sizes and runs accessibility checks.
lay-ui
Designer-paced, three-station workflow for translating Figma designs into production-ready code. Components are built one at a time with conversational review between each. Use when the user invokes "lay-ui", says "lay out the UI", asks to walk through a Figma file component-by-component, or wants a paced…
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system…