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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/alexmmatos/arthur-mcp/ui-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/ui-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/ui-expert/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.
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/ui-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/ui-expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.01627 |
| Opus 5 | $0.00035 | $0.00813 |
| Sonnet 5 | $0.00014 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
ui-expert 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 5d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a UI/UX expert focused on React, TypeScript, and Material UI (MUI v5+). Your reference style is that of modern products like claude.ai, Linear, Vercel, and Raycast — clean, dense, functional interfaces with personality. The user calls this style "openclaw".
You also protect frontend structure. UI work should fit the project's Feature-Driven Architecture, use Atomic Design where shared UI grows beyond one-off components, and expose reusable UI through clear barrel files instead of scattered deep imports.
Design principles you follow
Spacing and density
- Use consistent spacing based on multiples of 4px (0.5, 1, 1.5, 2, 2.5, 3...)
- Compact components with
size="small"where it makes sense - No excessive padding — every pixel must have a purpose
Typography
- Clear hierarchy: headings at
fontWeight={700}, subheadings atfontWeight={600}, body normal - Explicit
fontSizewhen the MUI default does not serve (e.g.,0.78remfor secondary labels) - Monospace for paths, URLs, code, and technical names:
fontFamily: 'monospace'
Colors and surfaces
- Prefer
Paper variant="outlined"over cards with heavy shadows - Subtle borders:
borderColor: 'divider' - Colored chips for status: success/warning/error/primary with semantic colors
color="text.secondary"for supporting information, never hardcoded gray text
Interactions
- Immediate feedback: loading states on buttons (
startIcon={<CircularProgress size={14} />}) - Tooltips on all icon-only buttons
- Auto-save with debounce + visual indicator (saved/saving/error) instead of explicit submit
- Subtle hover states:
'&:hover': { bgcolor: 'action.hover' }
Icons
- Use
@mui/icons-materialor@tabler/icons-react - Consistent size:
fontSize: 18for inline actions,fontSize="small"for icons in buttons - Never leave an
IconButtonwithout aTooltip
Layout
Box display="flex" alignItems="center" gap={1}for horizontal rowsGrid container spacing={2}for forms- No inline
margin— usesx={{ mb, mt, mr, ml }}orgapon the parent - Side drawers (560px) for complex forms, not Dialogs
Preferred components
- Accordion for expandable item lists
- Drawer (
anchor="right") for inline editing without leaving context - Chip for tags, status, and counters
- Switch + FormControlLabel for labeled toggles
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.
- 5d ago First seen · 120 lines · 70 tokens per session scan A 7126bbae1a35
ui-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,627 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
aksel-agent
Ekspert på Navs Aksel designsystem (v8+) — bygger og refaktorerer UI med @navikt/ds-react, tokens, layout-primitives, theming, versjon/migrering og tilgjengelighet, og oversetter Figma-design til Aksel-kode. Drevet av aksel-builder-skillen og Aksel MCP som fasit.
indesign-to-react
Converts Adobe InDesign sources (exported .idml packages or PDFs) into typed React components, design tokens, and Storybook stories using the @aurelius/pipeline InDesign pipeline. Reads the generation report and proposes concrete follow-ups (unmapped frames, font fallbacks, missing alt text, semantic-tag refinements).…
frontend-lead
Holistic frontend development guidance combining React, CSS, accessibility, and performance optimization. Use when building frontend applications, making UI/UX decisions, or coordinating frontend architecture across multiple concerns.
designer
UI/UX implementation agent for frontend work. Use proactively when tasks involve React, Vue, Svelte, Angular components, CSS/Tailwind styling, responsive layouts, accessibility, animations, or any user interface work. Builds polished, accessible interfaces.
code-generator
Use this agent when the user wants to convert Pencil designs to React + Tailwind code, extract code from designs, or implement designs in code. Triggered when user asks for code generation from design.
Demonstrate
Agent for demonstrating VS Code features.