agentmods.dev

UIX CLAUDE.md

A project guide for UIX, a monorepo—one repository containing several related packages—that provides a shared layer for turning AI output into user interfaces. It defines the project’s visual design rules, package structure, tools, and Git conventions.

In plain words
What is it for?
Use it when building UI components, choosing styles, working in the pnpm packages, running tests or builds, or writing commit messages.
Why use it?
It keeps changes consistent across packages and prevents UI code from using colours, shapes, or patterns that conflict with the project’s design system.

Instructions file

10 5mo ago A scan 365 tokens original MIT
View the source file Deepractice/UIX
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 instructions/deepractice/uix/claude-md
Clone the repo
git clone --depth 1 https://github.com/Deepractice/UIX
Per session 365 This file is loaded in full into every session.
When invoked 365 The same file — it is already loaded in full.
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 $0.00365 $0.00365
Opus 5 $0.00182 $0.00182
Sonnet 5 $0.00073 $0.00073
Haiku 4.5 $0.00036 $0.00036

Measured 3d ago against content hash b0c6f7704ee1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

UIX CLAUDE.md 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 3d 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.md · 43 lines

What it actually says

UIX Project Rules

This is the UIX monorepo — an AI-to-UI Intermediate Representation (IR) protocol layer.

Design System: Lucid UI

When generating any UI code in this project, follow the Lucid design system:

Colors

  • Primary: Rational Blue #0284c7 (NOT purple, NOT indigo)
  • Secondary: Sentient Gold #f59e0b
  • Background: White #FFFFFF (light) / Gray-900 #171717 (dark)
  • Text: Gray-700 #404040 on white, Gray-300 on dark

Forbidden

  • Purple/violet/fuchsia gradients
  • Neon colors
  • Rainbow gradients
  • rounded-3xl on everything
  • Decorative background blobs
  • Gradient buttons

Preferred Patterns

  • Solid color buttons with rounded-md
  • border border-gray-200 over heavy shadows
  • Inter font family
  • 4px grid spacing
  • Subtle animations (150-300ms)

Architecture

  • Monorepo with pnpm workspaces
  • Packages: core, agent, lucid-tokens, lucid-react, stream, adapter-vercel, adapter-agui, adapter-a2ui
  • Build: tsup (ESM only), Vite for apps
  • Test: vitest
  • Styling: Tailwind CSS

Git

  • Author: deepracticexc <[email protected]>
  • Conventional commits: feat:, fix:, docs:, style:, refactor:, test:

Full Design Rules

See skills/lucid-ui/SKILL.md for the complete design system specification.

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. 3d ago First seen · 43 lines · 365 tokens per session scan A b0c6f7704ee1

Subscribe to this mod's changes

UIX CLAUDE.md is an instructions file published in the GitHub repository Deepractice/UIX (10 stars, last pushed 5mo ago), licensed MIT. It adds 365 tokens to every session, about $0.0018 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.

CSS and stylingDesign and UXFrontendaiai-agentai-uiclaude-skillcursor-rulesdesign-system
Related

Other instructions, from other repositories

PixelPilot uiux-footer.instructions.md

Footer design, links, and site information.

dev-lou/PixelPilot · 8,172 tokens

PixelPilot uiux-consistent-navigation.instructions.md

Navbar and footer must be shared components. Active link highlighting uses route matching. Consistent styling across all pages.

dev-lou/PixelPilot · 4,885 tokens

PixelPilot uiux-css-architecture.instructions.md

CSS methodology, modules, and styling strategies.

dev-lou/PixelPilot · 5,197 tokens

PixelPilot uiux-loading-storytelling.instructions.md

Making wait times feel shorter through progress narratives, skeleton theatre, and entertaining loading states. Turning frustration into delight.

dev-lou/PixelPilot · 4,571 tokens

PixelPilot uiux-micro-interactions.instructions.md

Library of token-aware micro-interactions including ripple, skeleton loaders, toasts, pull-to-refresh, and drag-to-reorder. All respect prefers-reduced-motion.

dev-lou/PixelPilot · 5,219 tokens

PixelPilot uiux-motion.instructions.md

Animations, transitions, and motion design principles.

dev-lou/PixelPilot · 5,965 tokens