What is design-system-reference?

A frontend design reference containing style guides, implementation rules, common mistakes, and checklists for different visual styles. It is intended to be used after a design-discovery step, or directly when the desired style is already known.

Use it when building a frontend with a specified style, such as a dark Bento Grid landing page, to select the relevant guide and apply its layout, colors, components, and interaction rules.

It turns a chosen visual direction into concrete frontend decisions and implementation checks instead of leaving the style open to interpretation.

design-system-reference — Skill by wigtn

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 skills/wigtn/wigtn-plugins/design-system-reference

Any agent

npx skills add wigtn/wigtn-plugins --skill design-system-reference

Clone the repo

git clone --depth 1 https://github.com/wigtn/wigtn-plugins

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,045 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.

Model	Per session	Once invoked
Fable 5	$0.00043	$0.02045
Opus 5	$0.00022	$0.01022
Sonnet 5	$0.00009	$0.00409
Haiku 4.5	$0.00004	$0.00204

Measured 2d ago against content hash 0133d8aeb9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-system-reference 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 2d 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.

plugins/wigtn-plugins/skills/design-system-reference/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Implementation Guide

Overview

This skill provides style guides and implementation rules for frontend design.

For design discovery and style selection, use the design-discovery agent which:

Gathers context through step-by-step questions
Uses VS (Verbalized Sampling) technique to recommend styles with suitability percentages
Applies AIDA methodology for landing pages

This skill is automatically loaded after the agent completes discovery.

How to Use

With Discovery Agent (Recommended)

User requests frontend design
design-discovery agent conducts context gathering
Agent presents VS-based style recommendations
After style selection, agent loads this skill for implementation

Direct Usage (Quick Mode)

If user already knows their style, skip discovery:

"Build me a landing page with Bento Grid style, dark theme, minimal animations"

In this case, directly read the relevant style guide and implement.

Style Selection & Guidelines

Based on user responses, select the appropriate style and read the corresponding guide.

Read both the style guide and the relevant common modules before implementing.

Available Style Guides

Use the Read tool to read the corresponding style file:

Editorial → styles/editorial.md
Brutalist → styles/brutalist.md
Neobrutalism → styles/neobrutalism.md
Glassmorphism → styles/glassmorphism.md
Liquid Glass → styles/liquid-glass.md
Swiss Minimal → styles/swiss-minimal.md
Minimalism → styles/minimalism.md
Neomorphism → styles/neomorphism.md
Claymorphism → styles/claymorphism.md
Skeuomorphism → styles/skeuomorphism.md
Bento Grid → styles/bento-grid.md
Dark Mode First → styles/dark-mode-first.md
Minimal Corporate → styles/minimal-corporate.md
Retro Pixel → styles/retro-pixel.md
Organic Shapes → styles/organic-shapes.md
Maximalist → styles/maximalist.md
3D Immersive → styles/3d-immersive.md
Aurora / Gradient Mesh → styles/aurora-gradient.md
Terminal / Hacker → styles/terminal-hacker.md
Kinetic Typography → styles/kinetic-typography.md

Read the full file on GitHub · 234 lines

Files

What ships with it

24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2d ago First seen · 234 lines · 43 tokens per session scan A 0133d8aeb9fd

Subscribe to this mod's changes

design-system-reference is a skill published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 17d ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,045 once invoked, about $0.0002 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.

CSS and styling Design and UX Frontend agent-skills ai-native anthropic claude-code claude-code-plugin junior-developer

shadcn-ui

Provides complete shadcn/ui component library patterns including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, installing components, building forms with React Hook Form and Zod, customizing themes with Tailwind CSS, or implementing UI patterns like…

shep-ai/shep · 74 tokens

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

fabriqaai/specs.md · 43 tokens

ui-designer

Visual designer. Use when users need to design logos, icons, UI interfaces, page layouts, landing pages, component styles, color schemes, typography, or interaction animations. Also applies to "design me a...", "make something nice...", "create a visual concept..." scenarios. Even if user doesn't explicitly say…

korbinjoe/TeemAI · 128 tokens

frontend-expert

Frontend development expert proficient in React 18+, TypeScript 5+, and TailwindCSS. Automatically activates when users need frontend component development, styling, state management, or performance optimization.

korbinjoe/TeemAI · 41 tokens

ai-native-design

AI 原生 UI 设计与代码一体化工作流。3 通道（claude-design / figma / v0）从 design-brief.md 派生 prompt + 附件包，用户在外部工具完成迭代，DDT 摄取设计源后 main thread 改写为 web/ 项目契约对齐代码。由 /design-brief 与 /design-execute 自动加载；/build-web main thread 进入 IMPLEMENT phase 时加载。.

dhslegen/digital-delivery-team · 105 tokens

design-guide

Paperclip UI design system guide for building consistent, reusable frontend components. Use when creating new UI components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language and conventions. Covers: component creation, design…

paperclipai/paperclip · 105 tokens