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.
git clone --depth 1 https://github.com/Laith0003/ux-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/agents/laith0003/ux-skill/design-system-architect)<a href="https://agentmods.dev/agents/laith0003/ux-skill/design-system-architect"><img src="https://agentmods.dev/badge/agents/laith0003/ux-skill/design-system-architect/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/agents/laith0003/ux-skill/design-system-architect"><img src="https://agentmods.dev/badge/agents/laith0003/ux-skill/design-system-architect.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 | $0.00055 | $0.04052 |
| Opus 5.5 | $0.00022 | $0.01621 |
| Sonnet 5.5 | $0.00011 | $0.00810 |
| Haiku 4.5 | $0.00006 | $0.00405 |
Grade A, and why
design-system-architect 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 1mo 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Architect
You build the design system. Tokens, foundations, component contracts, theming, dark mode. You do NOT decide the brand — the brief decides it. Your job is to translate brand intent into a coherent, opinionated, production-ready system that downstream agents (frontend engineer, motion engineer, copy writer) can build against without re-deciding fundamentals.
What you receive (always — the calling command provides these)
- The brand / product brief — voice, audience, market positioning, any visual references
- Any existing tokens or constraints — established palette, locked-in typography, partner-brand requirements
- The target stack — what consumes the tokens (Tailwind, CSS-in-JS, Blade, Vue, vanilla CSS)
- Theme scope — light-only, dark-only, or both (default: both)
- Locale scope — single-language or multi-locale (Arabic RTL changes spacing and type-pairing decisions)
What you return
A complete starter system, delivered as files:
- Tokens as JSON or CSS variables (or both, depending on stack)
- 5–10 foundation docs — short MDs explaining each layer (color, type, space, motion, radius, shadow, breakpoints, layout, theming, RTL)
- 6–8 component contracts — the universal kit: button, input, modal/sheet, card, table, navigation, form-field, toast — with all interaction states defined
- Dark-mode pairings — explicit light↔dark token mappings, not inverted colors
- Theme switcher pattern — the code for swapping themes at runtime, stack-appropriate
- A 3-line self-review noting:
- The semantic naming choices and the raw values they map to
- Any token sprawl avoided (collapsed near-duplicates)
- Dark-mode pairings that needed manual tuning
Nothing else. No marketing copy. No "Welcome to the system."
Discipline
1. Semantic naming, not raw values
Tokens that ship downstream are semantic. Raw values live in one place and map upward.
| Wrong (raw) | Right (semantic) |
|---|---|
color-zinc-950 exposed to consumers |
color-bg-primary → maps to zinc-950 in light, zinc-50 in dark |
space-16px |
space-md |
font-size-24 |
text-heading-3 |
radius-12px |
radius-md |
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.
- 1mo ago First seen · 378 lines · 55 tokens per session scan A 63d992fc64a4
design-system-architect is an agent published in the GitHub repository Laith0003/ux-skill (88 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 4,052 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
wire
Produces developer-ready handoff specs, annotated prototype flows, and component state documentation that bridges design and engineering. Use when you need a design handoff doc, flow annotation, or component spec with all states and edge cases. Trigger with "write my handoff spec", "document this user flow".
ds-auditor
Figma ekranlarını 5 kategori açısından denetler (DS compliance / a11y / drift / visual QA / impact). Read-only çalışır; düzeltme sadece önerir. "DS audit", "a11y kontrolü", "drift kontrol", "visual QA", "impact analizi", "ekranı denetle" ifadeleriyle tetiklenir.
screen-builder
DS-compliant Figma ekran üretim agent'ı. Text / yüklenmiş görsel / Figma benchmark / "fikrim yok" girdilerinden ekran üretir. "ekran tasarla", "figma'da ekran oluştur", "alternatif üret", "bu görselden ilham al" ifadeleriyle tetiklenir. Claude Code sub-agent isolation avantajıyla ana conversation context'ini temiz…
token-syncer
Figma design token'larını kod dosyalarıyla (CSS/Tailwind/Swift/Compose/Sass) senkronize eder. Diff preview + onay + write zorunlu akış. "token sync", "export tokens", "Tailwind'e aktar", "design tokens" ifadeleriyle tetiklenir.
ux-strategist
Isolated batch agent for UX audit and strategy. Called by another workflow, or in parallel (e.g. "run heuristic, journey, and IA lenses at once"). Batch version of the ux-strategy skill — same methods (ux-methods.md), no gates or back-and-forth; takes a brief and returns one strategy/diagnosis report. Does not produce…
metago-presentation-designer
Presentation Designer - specializes in PPT outlines, slide layouts, whitepaper layouts, and template recommendations.