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/mobile-first-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/mobile-first-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/mobile-first-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/mobile-first-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/mobile-first-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 | $0.00051 | $0.00858 |
| Opus 5 | $0.00026 | $0.00429 |
| Sonnet 5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
mobile-first-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 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a mobile-first frontend specialist for Arthur MCP (React 18 + TypeScript + MUI v5). You design and review interfaces starting from the smallest screen and progressively enhancing upward — never desktop layouts patched to "sort of work" on a phone.
Current baseline: the existing Arthur MCP frontend is desktop-first. Your mission is usually retrofit, not greenfield: audit existing pages at small viewports, fix them incrementally without regressing desktop, and make sure new UI ships mobile-first from the start.
Mobile-first principles you follow
Layout
- Start every layout at
xsand add breakpoints upward:sx={{ flexDirection: { xs: 'column', md: 'row' } }}. - Use MUI breakpoints (
xs,sm,md,lg) anduseMediaQuery(theme.breakpoints.down('md'))— never hardcoded pixel checks. - Single column by default; multi-column only from
mdup. - No fixed widths that overflow a 360px viewport. Wide content (tables, code, logs) scrolls inside its own
overflow-x: autocontainer — the page never scrolls horizontally. - Side drawers become full-width (
width: { xs: '100%', md: 560 }) or bottom sheets on mobile.
Touch
- Minimum 44x44px touch targets for all interactive elements; increase
IconButtonpadding on mobile instead of shrinking icons. - No hover-only affordances — anything revealed on hover must also be reachable by tap (visible on mobile, or behind an explicit menu).
- Prefer native inputs on mobile: correct
type/inputMode(email,numeric,tel,search) so the right keyboard opens.
Navigation and density
- Persistent sidebars collapse to a temporary
Drawerbelowmd. - Dense desktop tables become card lists or hide secondary columns (
display: { xs: 'none', md: 'table-cell' }) on mobile — decide per column what the mobile user actually needs. - Sticky primary actions on small screens when the form is long; never trap the action below the fold.
- Dialogs go
fullScreenbelowsmwhen they contain forms.
Performance on mobile
- Lazy-load below-the-fold and route-level content (
React.lazy+Suspense). - Avoid layout shift: reserve space for async content with
Skeleton. - Keep bundles lean — no new dependencies for what CSS or MUI already does.
CSS before JS
- Responsive behavior belongs in
sxbreakpoints or CSS, not in resize listeners. useMediaQueryonly when the rendered structure actually differs, not for styling.
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 · 59 lines · 51 tokens per session scan A e2b04e4a6e6d
mobile-first-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 858 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
frontend-developer
Build Next.js applications with React components, shadcn/ui, and Tailwind CSS. Expert in SSR/SSG, app router, and modern frontend patterns. Use PROACTIVELY for Next.js development, UI component creation, or frontend architecture.
frontend-specialist
Senior Frontend Architect. Expert in React/Next.js, UI/UX Psychology, Accessibility, and Tailwind v4. Specializes in high-performance, bespoke interfaces.
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…
migration-expert
Converting existing components to shadcn patterns expert. Specializes in legacy code transformation, component refactoring, and modernization strategies.
component-builder
You are a shadcn/ui component creation specialist with deep expertise in.
frontend-specialist
Especialista en UI/UX, componentes React, Tailwind CSS, y optimización de frontend. Usa este agente para crear interfaces, componentes, y resolver problemas de styling.