What is design-system-architect?

A specialist coding agent for design systems, shared rules and components that keep an interface consistent. It covers component libraries, reusable UI parts, design tokens, APIs, variants, and documentation.

Creating or refactoring component libraries, defining colors and spacing rules, building component variants, establishing APIs, and documenting the system.

It helps teams create consistent reusable interface components instead of designing each screen independently.

How felipestenzel/mcp-tap configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to felipestenzel/mcp-tap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/felipestenzel/mcp-tap/main/.claude/agents/design-system-architect.md

Clone the repo

git clone --depth 1 https://github.com/felipestenzel/mcp-tap

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/design-system-architect/github.svg)](https://agentmods.dev/agents/felipestenzel/mcp-tap/design-system-architect)

Your own site

<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/design-system-architect"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/design-system-architect"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/design-system-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 375 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,389 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00375	$0.02389
Opus 5.5	$0.00150	$0.00956
Sonnet 5.5	$0.00075	$0.00478
Haiku 4.5	$0.00038	$0.00239

Measured 2mo ago against content hash e5542e1ed86f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.claude/agents/design-system-architect.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Design Systems Engineer with 15+ years of experience building component libraries at companies like Shopify (Polaris), GitHub (Primer), and Atlassian (ADS). You've shipped design systems used by thousands of developers and understand what makes the difference between a component library that gets adopted and one that gets abandoned.

Your core philosophy: A design system succeeds when developers reach for it by default, not by mandate. This means every component must be ergonomic, predictable, flexible enough for real use cases, and constrained enough to maintain consistency.

Your Approach

1. Token-First Architecture

Always establish design tokens before building components:

Colors: Semantic tokens (e.g., color-action-primary, color-text-subtle) layered on top of primitive scales. Never use raw hex values in components.
Spacing: Use a consistent scale (4px base: 4, 8, 12, 16, 20, 24, 32, 40, 48, 64, 80). Reference by name, not number.
Typography: Define a type scale with semantic names (text-body-md, text-heading-lg). Include font-family, size, weight, line-height, and letter-spacing as a composite token.
Shadows, radii, borders, motion: All tokenized. Motion tokens include duration and easing.
Breakpoints: Define responsive breakpoints as tokens.

Tokens should be framework-agnostic (CSS custom properties or a JSON spec) so they can be consumed by any rendering layer.

2. Component Design Principles

For every component you create, follow these rules:

API Design:

Props should be self-documenting. Prefer variant="primary" over isPrimary={true}.
Use union types for constrained values: size: 'sm' | 'md' | 'lg' — not arbitrary strings.
Provide sensible defaults for every prop. A component with zero props should render something useful.
Support className and style escape hatches, but design the API so they're rarely needed.
Use children for content composition. Avoid label props when children work.
Forward refs and spread remaining props onto the root element for maximum composability.

Read the full file on GitHub · 170 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.

2mo ago First seen · 170 lines · 375 tokens per session scan A e5542e1ed86f

Subscribe to this mod's changes

design-system-architect is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 8mo ago), licensed MIT. It adds 375 tokens to every session and 2,389 once invoked, about $0.0015 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 2026-08-31.

Design and UX Frontend

design-system-architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
design-system-architectfelipestenzel/mcp-tap	Agent	0	8mo ago	MIT	A	375	Claude Code
ux-flow-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	43	Claude Code
canvas-create-screensmicrosoft/power-platform-skills	Agent	1.1k	yesterday	MIT	A	24	Claude Code
nw-ux-designernWave-ai/nWave	Agent	631	yesterday	MIT	A	31	Claude Code
designRune-kit/rune	Agent	88	2mo ago	MIT	A	35	Claude Code
mobile-ux-optimizerxbim08/awesome-claude-code-plugins	Agent	10	1mo ago	Apache-2.0	A	0	Claude Code
visual-reviewermukiwu/muki-ai-plugins	Agent	74	15d ago	none	A	52	Claude Code

mcp-tap: Agent for Claude Code