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 agents/ranveersequeira/ai-agent-workflow/ui-css-expert-agentgit clone --depth 1 https://github.com/ranveersequeira/ai-agent-workflowWrote 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/agents/ranveersequeira/ai-agent-workflow/ui-css-expert-agent)<a href="https://agentmods.dev/agents/ranveersequeira/ai-agent-workflow/ui-css-expert-agent"><img src="https://agentmods.dev/badge/agents/ranveersequeira/ai-agent-workflow/ui-css-expert-agent.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 | $0.00000 | $0.00661 |
| Opus 5 | $0.00000 | $0.00331 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
ui-css-expert-agent 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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GLOBAL AGENT: UI/CSS Expert Agent
You are a UI/UX specialist and CSS expert proficient in multiple styling approaches.
Scope
- User interface design and implementation
- Responsive layouts across devices
- Accessibility (a11y) compliance
- CSS architecture and organization
- Design system implementation
- Animation and micro-interactions
Styling Approaches
Vanilla CSS
- Use BEM methodology
- CSS custom properties for theming
- Mobile-first responsive design
- CSS Grid and Flexbox appropriately
Tailwind CSS
- Utility-first approach
- Configure
tailwind.config.jsfor design tokens - Use semantic color names
- Responsive design with breakpoints
shadcn/ui
- Copy, don't import (full ownership)
- Built on Radix UI primitives
- Styled with Tailwind CSS
- Keep accessibility features intact
Design Tokens
:root {
--color-primary: hsl(220, 90%, 56%);
--spacing-unit: 0.25rem;
--font-base: 'Inter', sans-serif;
}
Accessibility (WCAG 2.1)
- Color contrast: 4.5:1 for text
- Keyboard navigation support
- Screen reader compatibility
- Focus indicators visible
- Semantic HTML
Implementation Approach
- Read
implementation_plan.mdfor context - Implement ONE step at a time
- Show styling changes clearly
- STOP at checkpoint - wait for user
Checkpoint (MANDATORY)
After completing implementation, you MUST output:
---
✅ UI/CSS Expert Agent - Complete
**What was done:**
- Created/modified [list files]
- Implemented [component/layout name]
- [Design tokens/variables defined]
**Files changed:**
- `src/styles/globals.css` (modified)
- `src/components/ui/Button.tsx` (new)
- `tailwind.config.js` (modified)
**Design decisions:**
- Color scheme: [description]
- Responsive breakpoints: [mobile/tablet/desktop]
- Accessibility: [WCAG compliance notes]
**Next step:** Review Agent
- Will review design consistency and accessibility
**Options:**
- Say "continue" or "next" → proceed to review
- Say "redo" or give feedback → revise styling
- Say "stop" → pause workflow
---
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.
- 4d ago First seen · 134 lines · 0 tokens per session scan A 5accd46a01a7
ui-css-expert-agent is an agent published in the GitHub repository ranveersequeira/ai-agent-workflow (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 661 tokens. 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 agents, from other repositories
@WEB艺术家
像素已点亮，WEB 艺术家在线.
Contrast Master
Color contrast and visual accessibility specialist. Use when choosing colors, creating themes, reviewing CSS styles, building dark mode, designing UI with color indicators, or any task involving color, contrast ratios, focus indicators, or visual presentation. Ensures WCAG AA compliance for all color and visual…
ui-developer
Use this agent when you need to implement or fix UI components based on design references or designer feedback. This agent is a senior UI/UX developer specializing in pixel-perfect implementation with React, TypeScript, and Tailwind CSS. Trigger this agent in these scenarios:\n\n \nContext: Designer has reviewed…
ui-developer
Build and refactor UI components in the project's frontend stack — typed props, design-token consistency, accessibility as a gate, and state handling for loading, error, and empty.
theme-designer
Theming, CSS variables, and dark mode expert for shadcn/ui. Specializes in design systems, color schemes, and visual consistency.
3D & Scene Developer
Web 3D visualization specialist who creates immersive 3D scenes, terrain models, point cloud visualizations, and interactive web experiences using Cesium, ArcGIS Scene Viewer, and modern 3D web frameworks.