design-system-architect

design-system-architect is an agent for Claude Code from Laith0003/ux-skill. It costs 55 tokens per session (4,052 once invoked), scanned A, original, MIT.

An agent that builds a design system: the shared rules for colors, typography, spacing, shapes, shadows, motion, themes, and reusable components. It can prepare these rules for stacks such as Tailwind, Vue, or plain CSS.

In plain words
What is it for?
Use it to turn a brand or product brief into design tokens, foundation documents, component contracts, theme support, dark mode, and right-to-left language guidance.
Why use it?
It prevents each screen or developer from making separate visual decisions, improving consistency across the product.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ux plugin — 25 commands, 5 agents shipped together

Install

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.

agentmods
npx agentmods add agents/laith0003/ux-skill/design-system-architect
Clone the repo
git clone --depth 1 https://github.com/Laith0003/ux-skill

Made for: Claude Code.

Or install ux, the plugin that ships this one along with the rest of its 25 commands, 5 agents.

Wrote 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.

agentmods badge for design-system-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/laith0003/ux-skill/design-system-architect.svg)](https://agentmods.dev/agents/laith0003/ux-skill/design-system-architect)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,052 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.04052
Opus 5 $0.00028 $0.02026
Sonnet 5 $0.00011 $0.00810
Haiku 4.5 $0.00006 $0.00405

Measured 6d ago against content hash 63d992fc64a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

agents/design-system-architect.md · 378 lines

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)

  1. The brand / product brief — voice, audience, market positioning, any visual references
  2. Any existing tokens or constraints — established palette, locked-in typography, partner-brand requirements
  3. The target stack — what consumes the tokens (Tailwind, CSS-in-JS, Blade, Vue, vanilla CSS)
  4. Theme scope — light-only, dark-only, or both (default: both)
  5. 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:

  1. Tokens as JSON or CSS variables (or both, depending on stack)
  2. 5–10 foundation docs — short MDs explaining each layer (color, type, space, motion, radius, shadow, breakpoints, layout, theming, RTL)
  3. 6–8 component contracts — the universal kit: button, input, modal/sheet, card, table, navigation, form-field, toast — with all interaction states defined
  4. Dark-mode pairings — explicit light↔dark token mappings, not inverted colors
  5. Theme switcher pattern — the code for swapping themes at runtime, stack-appropriate
  6. 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

Read the full file on GitHub · 378 lines

Changes

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.

  1. 6d ago First seen · 378 lines · 55 tokens per session scan A 63d992fc64a4

Subscribe to this mod's changes

design-system-architect is an agent published in the GitHub repository Laith0003/ux-skill (66 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 4,052 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 2026-08-30.

Related

Other agents, from other repositories

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.

atezer/FMCP · 72 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

fec-figma-implementer

Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six design tools: Figma, Sketch, MasterGo, Pixso, Ink Knife, and Mockup. Provide design draft links, selection screenshots or annotation data, automatically obtain…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens

frontend-ui-component-agent

/ui-component-agent or @ui-component-agent.

girijashankarj/cursor-handbook · 0 tokens

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…

atezer/FMCP · 91 tokens