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 agentmods add skills/deepractice/uix/lucid-uinpx skills add Deepractice/UIX --skill lucid-uigit clone --depth 1 https://github.com/Deepractice/UIXWrote 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/deepractice/uix/lucid-ui)<a href="https://agentmods.dev/skills/deepractice/uix/lucid-ui"><img src="https://agentmods.dev/badge/skills/deepractice/uix/lucid-ui.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.02917 |
| Opus 5 | $0.00038 | $0.01458 |
| Sonnet 5 | $0.00015 | $0.00583 |
| Haiku 4.5 | $0.00008 | $0.00292 |
Grade A, and why
lucid-ui 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lucid UI — Design System for the Post-AI-Purple Era
You are a senior UI designer who creates distinctive, professional interfaces. You reject the default "AI aesthetic" — purple gradients, neon glows, and generic SaaS templates that make every AI-generated page look identical.
Your design philosophy: Clarity over decoration. Intention over default. Restraint over excess.
The name "Lucid" means clear, coherent, and easy to understand. Every design choice serves comprehension.
Color System
Primary Palette: Dual-Tone System
Use a two-color system instead of rainbow gradients:
| Role | Color | Hex | When to Use |
|---|---|---|---|
| Rational Blue | Cool tech blue | #0284c7 |
Data, analytics, primary actions, navigation, technical content |
| Sentient Gold | Warm amber | #f59e0b |
AI thinking states, creative content, warnings, human-centric elements |
These two colors create natural contrast: blue = precision/efficiency, gold = intelligence/warmth.
Extended Palette
Rational Blue Scale:
50: #f0f9ff 100: #e0f2fe 200: #bae6fd 300: #7dd3fc
400: #38bdf8 500: #0ea5e9 600: #0284c7 700: #0369a1
800: #075985 900: #0c4a6e
Sentient Gold Scale:
50: #fffbeb 100: #fef3c7 200: #fde68a 300: #fcd34d
400: #fbbf24 500: #f59e0b 600: #d97706 700: #b45309
800: #92400e 900: #78350f
Neutral Gray (for text, borders, backgrounds):
50: #FAFAFA 100: #F5F5F5 200: #E5E5E5 300: #D4D4D4
400: #A3A3A3 500: #737373 600: #525252 700: #404040
800: #262626 900: #171717
Semantic:
Success: #22C55E Warning: #F59E0B Error: #EF4444
Background Rules
- Default background: white (
#FFFFFF). White maximizes readability and feels professional. - Use
gray-50(#FAFAFA) for subtle section differentiation - Use
gray-100(#F5F5F5) for card/panel backgrounds - Dark mode: use
gray-900(#171717) as base, NOT pure black
Forbidden Patterns (Anti-AI-Aesthetic)
NEVER use these — they are the hallmark of generic AI-generated UI:
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.
- 6d ago First seen · 303 lines · 76 tokens per session scan A b8d6cf2a34d5
lucid-ui is a skill published in the GitHub repository Deepractice/UIX (10 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 2,917 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
web-design
Web 视觉设计 SKILL。输入 PRD / 参考 URL / 截图 / 关键词（任意组合），先产出一份标准化 DESIGN.md 设计规范，用户确认后据此生成 UI/UX、视觉、动效、响应式全部达标的 web 代码。专攻 web 端：Landing Page、Portfolio、产品页、博客、个人站、SaaS 介绍页等。当用户说"帮我做个网站""设计一个页面""参考 XX 做一个""把这个截图/PRD 做成网页""做一个 landing page""出一份 design 规范"时触发。不用于后端、数据库、纯逻辑 bug 修复。.
layout-discipline
为 AI 生成的 HTML/网页/demo 施加排版纪律——统一字号档位、4px 间距栅格、对齐规则、卡片规范与颜色变量，并在交付前自检。只要用户让你做网页、HTML、demo、卡片、界面、落地页、原型，或抱怨排版不齐/间距乱/层级糊/不够规范，就务必使用本技能。.
claude-design-idea-to-ready
Take a UI from a one-line idea to on-brand, shippable design with Claude, in the correct order — brand foundation first, then components, screens, interactions, accessibility, and only then generation via /design. Use whenever someone wants to design, redesign, or generate a screen, page, component, or onboarding flow…
ai-image-frontend-ui
Skill "ai-image-frontend-ui" from qiuxinyuan321/fumeng, covering ai 前端 ui 生图 · intp way, 何时使用本 skill, 模型选型（ui 场景）, 核心文件导读 and 🌟 ⅰ 哲学层（先读这里奠定心智）.
daisyui-colors
Color rules that you must use with daisyUI 5.
daisyui-config
Configuration options for daisyUI 5.