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 5.5 | $0.00028 | $0.00651 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 3mo ago), licensed MIT. It adds 70 tokens to every session and 1,627 once invoked, about $0.0003 per session on Opus 5.5. 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
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
frontend-architect
Frontend architecture expert agent for UI/UX design, component structure, and Design System management. Handles React, Next.js, and modern frontend patterns. Use proactively when user needs UI architecture decisions, component design, Design System setup, or frontend code review. Triggers: frontend, UI architecture…
product-owner
Product Owner. Validates business value, functional requirements, and UX. Use for features, business-rule changes, and user-facing surfaces.
accessibility-reviewer
Review React components for accessibility issues (ARIA, keyboard navigation, screen readers, WCAG compliance). Use when reviewing forms, interactive components, or when accessibility is a concern.
frontend-specialist
Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.