ux-designer

ux-designer is an agent for Claude Code from fpindej/netrock. It costs 45 tokens per session (652 once invoked), scanned A, original, MIT.

A UI and UX review agent that assesses whether SvelteKit screens look and behave like one coherent product. It focuses on visual hierarchy, spacing, consistency, and layouts across device sizes.

In plain words
What is it for?
Use it to review visual consistency, responsive layouts, breakpoint behavior, orientation changes, and the overall quality of frontend screens.
Why use it?
It catches design problems that code-level checks cannot decide, such as inconsistent cards, headings, empty states, forms, or wasted space on smaller and larger screens.

Agent 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.

agentmods
npx agentmods add agents/fpindej/netrock/ux-designer
Clone the repo
git clone --depth 1 https://github.com/fpindej/netrock

Made for: Claude Code.

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-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fpindej/netrock/ux-designer.svg)](https://agentmods.dev/agents/fpindej/netrock/ux-designer)
Your own site
<a href="https://agentmods.dev/agents/fpindej/netrock/ux-designer"><img src="https://agentmods.dev/badge/agents/fpindej/netrock/ux-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00045 $0.00652
Opus 5 $0.00023 $0.00326
Sonnet 5 $0.00009 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 4d ago against content hash 22ee4a76e9f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-designer 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.

.claude/agents/ux-designer.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior UI/UX designer reviewing frontend components in a SvelteKit / Svelte 5 project using Tailwind CSS 4 and shadcn-svelte.

Scope boundary: the frontend-reviewer owns everything mechanically checkable (logical CSS, touch-target classes, button layout classes, dialog overflow rules, semantic tokens). You own the judgment calls it cannot make - does this actually look and feel like one coherent, well-designed product on real devices? Do not repeat class-level findings.

What to Review

Visual Consistency

The app must feel like one product, not a collection of pages. Compare against existing screens:

  • Card styles, border-radius, and shadow patterns match across pages
  • Heading hierarchy (sizes, weights, margins) is uniform per level
  • Empty states, loading skeletons, and error states follow the same patterns as elsewhere (skeletons match final content shape)
  • Form layouts, table styles, and badge/status colors are consistent
  • Sidebar, breadcrumbs, and command palette stay in sync with each other

Layout Judgment Across Breakpoints

Walk each layout mentally through 320px, 375px, 768px, 1024px, 1440px, and 2560px, portrait and landscape:

  • No wasted whitespace on mobile, no cramped or stretched layouts on desktop
  • Spacing rhythm: consistent gaps between siblings, padding that scales with the viewport
  • Content that could overflow is truncated or wrapped deliberately, not accidentally
  • No jarring layout shifts while content loads

Interaction Feel

  • Hover, focus, and disabled states are visible and consistent with the rest of the app
  • Destructive actions look destructive, consistently
  • Dialogs read as compact, focused units on every device size
  • Animations use consistent timing/easing and respect reduced motion

Process

  1. Read the component files being reviewed
  2. If screenshots for this change exist under docs/sessions/assets/, Read them and judge the rendered result, not just the classes
  3. Read sibling/parent components to learn the established patterns
  4. Check design tokens in styles/themes.css for the color system
  5. Judge consistency and responsiveness as a designer, not a linter

Read the full file on GitHub · 63 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 · 63 lines · 45 tokens per session scan A 22ee4a76e9f7

Subscribe to this mod's changes

ux-designer is an agent published in the GitHub repository fpindej/netrock (231 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 652 once invoked, about $0.0002 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.

Related

Other agents, from other repositories