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.
/plugin marketplace add tom-barkan/ux-advisor-pluginnpx agentmods add plugins/tom-barkan/ux-advisor-plugin/ux-advisor-plugingit clone --depth 1 https://github.com/tom-barkan/ux-advisor-pluginGrade 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.
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/"
}
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.
- 2d ago First seen · 26 lines scan A fbd6db16a577
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.
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.
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…
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.
blushu-design-skills
A modular design workflow for building and refining thoughtful websites.
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).
journey-mapper marketplace
Service design journey mapping skills for Claude Code.