ux-advisor

A user-interface and user-experience helper that researches established design systems and shows at least three interface options in interactive HTML previews.

In plain words
What is it for?
Use it to explore solutions for UX or UI problems and create an implementation plan suited to your codebase.
Why use it?
It helps replace guesswork about common interface patterns with researched alternatives you can compare.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add tom-barkan/ux-advisor-plugin
agentmods
npx agentmods add plugins/tom-barkan/ux-advisor-plugin/ux-advisor-plugin
Clone the repo
git clone --depth 1 https://github.com/tom-barkan/ux-advisor-plugin

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

ux-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 2d 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.

.claude-plugin/plugin.json · 26 lines

What it actually says

{
  "name": "ux-advisor",
  "version": "1.0.0",
  "description": "Solve UX/UI problems by researching how top design systems (Material, Apple HIG, Fluent, Polaris, etc.) handle similar patterns, presenting 3+ visual solutions as interactive HTML previews, and creating implementation plans tailored to your codebase.",
  "author": {
    "name": "Tom Barkan",
    "url": "https://github.com/tom-barkan"
  },
  "homepage": "https://github.com/tom-barkan/ux-advisor-plugin",
  "repository": "https://github.com/tom-barkan/ux-advisor-plugin",
  "license": "MIT",
  "keywords": [
    "ux",
    "ui",
    "design",
    "design-systems",
    "accessibility",
    "user-experience",
    "material-design",
    "apple-hig",
    "fluent-ui",
    "wcag"
  ],
  "skills": "./skills/"
}
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. 2d ago First seen · 26 lines scan A fbd6db16a577

Subscribe to this mod's changes

ux-advisor is a plugin published in the GitHub repository tom-barkan/ux-advisor-plugin (2 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories

ux-skill

Design intelligence engine for AI coding. v3 ships THE BRAIN: a deterministic 7-axis synthesizer (warmth, contrast, density, geometry, formality, motion, typepersonality) that compiles a novel design language per brief — no LLM calls, fully offline, closed-loop learning via a local decisions ledger. 1,243 structured e.

Laith0003/ux-skill · not measured

super-ux

Scenario-driven UI development: a versioned design chain in docs/ux/ — product vision -> personas, JTBD, journeys and stories -> user flows -> a screens+states UI map with Figma frames -> traced use-case scenarios -> evidence-backed audits -> concrete fix plans. Skills: vision, ux-foundation, ux-flows, ux-scenarios…

ssheleg/super-ux · not measured

uxi

Ask it for a fake countdown timer and it says no. A UX and accessibility skill for Claude Code: surface-class-aware audits, WCAG 2.2 checks, deceptive-pattern screening, and five zero-dependency lint and stats tools.

ahammadnafiz/uxi · not measured

blushu-design-skills

A modular design workflow for building and refining thoughtful websites.

MrBlushu/blushu-design-skills · not measured

ux-pilot

UX co-pilot — conversational UX designer with live preview. 376 rules, 161 palettes, 57 font pairings, 67 styles. Phases: Discovery (ABCD questions), Audit (code scan + scored report), Preview (local server + named versions), Export (spec + React/Svelte/Vue components).

Sakaax/ux-pilot · not measured

journey-mapper marketplace

Service design journey mapping skills for Claude Code.

joeyvansommeren/journey-mapper · not measured