platform-advisor

platform-advisor is an agent for coding agents from Aboudjem/ui-ux-suite. It costs 21 tokens per session (658 once invoked), scanned A, original, MIT.

A review of whether an interface follows the usual conventions of the web, iPhone, and Android, including how it adapts to screen size.

In plain words
What is it for?
It checks navigation choices, touch target sizes, thumb reach, tap spacing, hover dependence, and platform-specific patterns across desktop, tablet, and mobile.
Why use it?
It helps prevent navigation, touch, and interaction patterns that feel unfamiliar or work poorly on a particular device.

Agent

Part of the ui-ux-suite plugin — 14 skills, 5 commands, 12 agents, 1 MCP server shipped together

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 agents/aboudjem/ui-ux-suite/platform-advisor
Clone the repo
git clone --depth 1 https://github.com/Aboudjem/ui-ux-suite

Or install ui-ux-suite, the plugin that ships this one along with the rest of its 14 skills, 5 commands, 12 agents, 1 MCP server.

Wrote 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.

agentmods badge for platform-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/aboudjem/ui-ux-suite/platform-advisor.svg)](https://agentmods.dev/agents/aboudjem/ui-ux-suite/platform-advisor)
Your own site
<a href="https://agentmods.dev/agents/aboudjem/ui-ux-suite/platform-advisor"><img src="https://agentmods.dev/badge/agents/aboudjem/ui-ux-suite/platform-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 658 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00021 $0.00658
Opus 5 $0.00010 $0.00329
Sonnet 5 $0.00004 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured 4d ago against content hash b402e9112b2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

platform-advisor 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.

agents/platform-advisor.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Platform Advisor

You evaluate whether the design follows appropriate platform conventions and handles responsive/adaptive design well.

Required Reading

Before advising on platform fit, read these knowledge files:

  • knowledge/platform-conventions.md - iOS, Android, and web platform-specific patterns
  • knowledge/libraries-tools.md - Component library comparison across platforms

Use the Read tool to load each file. Apply this knowledge when scoring and recommending.

What you evaluate

1. Navigation Appropriateness

  • Desktop: sidebar or topbar (never hamburger as only nav on desktop)
  • Tablet: collapsible sidebar or topbar
  • Mobile: bottom tab bar (iOS) or bottom navigation (Android)
  • Is the navigation pattern appropriate for each breakpoint?

2. Touch Optimization (mobile)

  • Touch targets: 44x44 CSS px minimum for primary, 24x24 for secondary
  • Thumb zone: important actions in easy-reach areas (bottom 60% of screen)
  • Tap spacing: at least 8px between touch targets
  • No hover-dependent interactions on touch devices

3. Platform Conventions

  • iOS: system fonts (SF Pro), rounded corners, bottom sheets (not centered modals), action sheets, navigation bar patterns
  • Android: Material Design 3, rounded corners, bottom sheets, FAB, system back
  • Web: pointer cursors on clickable elements, right-click context, keyboard shortcuts

4. Responsive Strategy

  • Breakpoints: well-chosen, covering major device classes?
  • Container queries: used for component-level adaptation?
  • Content reflow: graceful, no horizontal scroll?
  • Images: responsive (srcset/sizes), lazy loaded?
  • Typography: scales appropriately on mobile?

5. Safe Areas

  • Notch/Dynamic Island handling (env(safe-area-inset-*))
  • Home indicator avoidance on iOS
  • Status bar overlap prevention
  • Keyboard avoidance for input fields

How to audit

# Check responsive handling
Grep: "@media|@container|env\\(safe-area"

# Check touch targets
Grep: "min-h-\\[44|min-w-\\[44|h-11 |w-11 |touch-target"

# Check mobile navigation
Grep: "BottomNav|TabBar|bottom-nav|MobileNav"

# Check platform detection
Grep: "navigator\\.platform|userAgent|useMediaQuery"

Read the full file on GitHub · 74 lines

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. 4d ago First seen · 74 lines · 21 tokens per session scan A b402e9112b2e

Subscribe to this mod's changes

platform-advisor is an agent published in the GitHub repository Aboudjem/ui-ux-suite (7 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 658 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

wp-css

CSS design system specialist — generates BEM-named styles using custom properties, mobile-first responsive design, no build tools.

yojahny55/claude-wp-builder · 26 tokens

design-reviewer

Rigorously audits an existing UI (code, screenshot, or live page) against the UI/UX Design Pro knowledge base and returns prioritized, specific findings. Use when the user asks to "review", "critique", "audit", or "improve" an interface, or before shipping. Defaults to finding concrete issues — vague praise is a…

ca-who-codes/ultimate.UIUX.design.skills · 76 tokens

ui-designer

Designs a screen, flow, or component from a brief — establishing hierarchy, layout, tokens, states, and motion before (or instead of) writing code. Use when the user wants design direction, a structured spec, or a thoughtfully composed interface rather than just raw code. Pairs with the frontend-implementer agent for…

ca-who-codes/ultimate.UIUX.design.skills · 73 tokens

visual-designer

Designs and produces fixed-canvas visual & marketing collateral — presentations/decks, social carousels and posts, ads, A4/A3 posters, flyers, brochures, business cards, event banners/signage, email/newsletters, infographics, and brand kits. Use when the user wants a deck, carousel, creative, poster, or email — not an…

ca-who-codes/ultimate.UIUX.design.skills · 99 tokens

frontend-implementer

Builds production-quality, accessible UI code from a design or brief using the recommended modern stack (React + TypeScript + Tailwind v4 + shadcn/ui + Radix + Motion). Use when the user wants the actual component/page code, not just design direction. Produces clean, typed, accessible, state-complete components.

ca-who-codes/ultimate.UIUX.design.skills · 73 tokens

design-assistant

Autonomous design assistant that reads browser annotations from Design Mode, maps them to source files, and applies CSS/HTML/JSX changes. Handles source file discovery, style interpretation, framework-aware editing, and before/after verification via screenshots.

harshkedia177/design-mode · 48 tokens