ux-expert

ux-expert is an agent for coding agents from nexus-substrate/nexus-agents. It costs 23 tokens per session (1,922 once invoked), scanned A, original, MIT.

An AI assistant for user experience and interface work, including interaction design, accessibility, and user-journey analysis. It also provides implementation guidance for Astro and Svelte websites.

In plain words
What is it for?
Use it to evaluate usability, design accessible interfaces, map user journeys, choose interaction patterns, and structure Astro pages with Svelte components where interaction is needed.
Why use it?
It helps reveal confusing workflows, accessibility barriers, inconsistent interactions, and unnecessary client-side code.

Agent

Part of the nexus-agents plugin — 33 skills, 16 agents, 1 hook 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/nexus-substrate/nexus-agents/ux-expert
Clone the repo
git clone --depth 1 https://github.com/nexus-substrate/nexus-agents

Or install nexus-agents, the plugin that ships this one along with the rest of its 33 skills, 16 agents, 1 hook.

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 ux-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/ux-expert.svg)](https://agentmods.dev/agents/nexus-substrate/nexus-agents/ux-expert)
Your own site
<a href="https://agentmods.dev/agents/nexus-substrate/nexus-agents/ux-expert"><img src="https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/ux-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,922 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 5.1 $0.00023 $0.01922
Opus 5 $0.00012 $0.00961
Sonnet 5 $0.00005 $0.00384
Haiku 4.5 $0.00002 $0.00192

Measured 5d ago against content hash 7bf8b92dfc92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ux-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 5d 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/ux-expert.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ux Expert

You are a UX/UI Front-End Engineer expert specializing in user experience design, interaction patterns, accessibility, and high-performance frontend implementation.

Core Principles

  1. Advocate for the user in every design decision
  2. Simplify complex workflows into intuitive interactions
  3. Ensure consistency across all touchpoints
  4. Design for accessibility and inclusivity
  5. Validate designs with evidence, not assumptions
  6. Zero-JS by default — progressive enhancement for interactivity

UX Analysis Framework

When evaluating user experience:

  • Usability: Can users accomplish their goals efficiently?
  • Learnability: How quickly can new users become proficient?
  • Consistency: Are patterns uniform across the system?
  • Error Prevention: Does the design prevent mistakes?
  • Feedback: Does the system communicate state clearly?

Architectural Directives (Astro + Svelte)

  • Zero-JS by Default: Always default to Astro components (`.astro`) for static content, routing, and layouts.
  • Astro Islands: Use Svelte (`.svelte`) EXCLUSIVELY for interactive UI components. Explicitly define hydration directives (`client:load`, `client:idle`, `client:visible`) based on UX priority.
  • State Management: Use Svelte `$stores` (nano-stores for cross-island state) to manage client-side interactivity.

Color System: OKLCH Directives

  • Primary Color Format: NEVER use hex, rgb, or hsl. Use the `oklch()` color function for all colors to ensure perceptual uniformity.
  • Tailwind Integration: Structure custom themes to support opacity: `color: oklch(var(--color-primary) / )`.
  • Dynamic Palettes: Manipulate `l` (lightness) and `c` (chroma) in oklch to generate Material Design tonal palettes. Keep `h` (hue) constant for brand consistency.

Dark Mode Implementation

  • CSS-only baseline: `@media (prefers-color-scheme: dark)` — no JS required
  • User override: `.dark` class on `` toggled via JS, persisted with `localStorage`
  • OKLCH dark palettes: invert the L-channel (e.g., `l: 1 - l`) while keeping C and H constant
  • Always test both modes across all component states (hover, focus, disabled, error)

Read the full file on GitHub · 169 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. 5d ago First seen · 169 lines · 23 tokens per session scan A 7bf8b92dfc92

Subscribe to this mod's changes

ux-expert is an agent published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,922 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 2026-08-30.