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.
npx skills add tom-barkan/ux-advisor-plugin --skill ux-advisorgit clone --depth 1 https://github.com/tom-barkan/ux-advisor-pluginWrote 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/skills/tom-barkan/ux-advisor-plugin/ux-advisor)<a href="https://agentmods.dev/skills/tom-barkan/ux-advisor-plugin/ux-advisor"><img src="https://agentmods.dev/badge/skills/tom-barkan/ux-advisor-plugin/ux-advisor.svg" alt="Measured on agentmods" 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 | $0.00178 | $0.02878 |
| Opus 5 | $0.00089 | $0.01439 |
| Sonnet 5 | $0.00036 | $0.00576 |
| Haiku 4.5 | $0.00018 | $0.00288 |
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 8d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user has a UX/UI problem they need solved. You are the orchestrator — you manage the conversation with the user and delegate heavy lifting to specialized subagents. This keeps things fast and thorough.
The UX problem
$ARGUMENTS
Phase 1: Discovery
This phase runs in the main conversation — you need to interact with the user directly.
1a: Scan the codebase (subagent)
While you prepare your questions, spawn an Explore subagent in the background to scan the codebase for context:
Subagent prompt: "Analyze this codebase for UX-relevant context. Find and report:
1. Frontend framework (check package.json, imports, build config)
2. Component library in use (MUI, Radix, shadcn, Ant Design, Chakra, etc.)
3. Styling approach (CSS modules, Tailwind, styled-components, SCSS, etc.)
4. Existing design tokens, theme files, or style configurations
5. Current implementation of [the feature in question] if it exists
6. Any existing UI patterns or component conventions used in the project
Report all findings in a structured summary."
1b: Interview the user
While the codebase scan runs in the background, ask the user clarifying questions. Tailor your questions to the problem — don't ask every question, just the ones that matter:
- Platform & device targets — Web, mobile (iOS/Android), desktop? Responsive or fixed?
- Design theme & brand — Dark/light mode? Brand colors? Existing design system or Figma file?
- Current experience — URL, screenshot, or file showing what exists now? What's not working?
- Users — Technical or non-technical? Frequency of use? Accessibility requirements?
- Scale & data — How much data? Edge cases (empty, thousands of items, long text)?
- Constraints — Offline support, RTL, performance budget, must match existing patterns?
When the codebase scan completes, incorporate its findings. Confirm assumptions with the user (e.g., "I can see you're using React + Tailwind with shadcn/ui — is that correct?").
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.
- 8d ago First seen · 283 lines · 178 tokens per session scan A 9ade8060b072
ux-advisor is a skill published in the GitHub repository tom-barkan/ux-advisor-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 178 tokens to every session and 2,878 once invoked, about $0.0009 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.
Other skills, from other repositories
refine-live
In-chat fallback for the Timeline Inspector Refine agent. Use when the user runs /refine live, asks to "refine live", "go live", or answer refine jobs — but ONLY when no persistent agent is wired (no npx transitions-refine live). Prefer npx transitions-refine live for run-and-forget (relay spawns agent per click, no…
transitions-dev
Production-ready CSS transitions for web apps. Use when implementing notification badges, dropdowns, modals, panel reveals, page transitions, card resizes, number pop-ins, text swaps, icon swaps, success checks, avatar group hovers, error state shakes, search/input clear, skeleton loaders, shimmer text, sliding tabs…
transitions-polish
Polish and refine existing motion against the transitions.dev motion-token scale — duration, distance, scale, blur, and easing — plus the rules for WHEN each token applies (open/close asymmetry, hover-in vs hover-out, stagger offsets, and intent delays). An add-on to the transitions-dev skill, focused on tuning what…
vois-tokens
Rules and patterns for building UI with shadcn/ui, Tailwind v4 or StyleX, and Motion against a Vois design token set. Use when building components, pages, or any UI that should conform to the workspace design system. Covers spacing, typography, color tokens, component architecture, animation, accessibility, and modern…
design-rationale
Help designers articulate the cognitive science, behavioral psychology, and platform standards behind their design decisions. Use this skill when a designer needs to explain why they made a decision in a critique, design review, or stakeholder meeting. Also use when auditing a screen for principle alignment, preparing…
righter
Apply UX content writing principles to review existing UI copy or write new UI copy from scratch. Use this skill whenever someone asks you to: review, audit, critique, or improve UI text, error messages, button labels, tooltips, empty states, onboarding copy, form helper text, or any software interface copy. Also…