A command that chooses a suitable UI/UX task for a web interface, such as checking layouts, interaction states, accessibility, or design-system consistency.

Use it to inspect responsive layouts, loading and error states, accessibility, user journeys, readability, and shared design rules, or to plan and apply interface cleanup.

It removes the need to know which specialised design check to run. It also helps separate read-only audits, planning, and changes that can be applied immediately.

uiux — Command for Claude Code by kensaurus: A command that chooses a suitable UI/UX task for…

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 commands/kensaurus/cursor-kenji/uiux

Clone the repo

git clone --depth 1 https://github.com/kensaurus/cursor-kenji

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/uiux.svg)](https://agentmods.dev/commands/kensaurus/cursor-kenji/uiux)

Your own site

<a href="https://agentmods.dev/commands/kensaurus/cursor-kenji/uiux"><img src="https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/uiux.svg" alt="Measured on agentmods" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 651 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00651
Opus 5	$0.00012	$0.00326
Sonnet 5	$0.00005	$0.00130
Haiku 4.5	$0.00002	$0.00065

Measured 2d ago against content hash f1a0aed5e8e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

uiux 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.

commands/uiux.md · 45 lines

What it actually says

/uiux

Discover existing system → detect rogue implementations → fix → validate.

This command is a thin entry point. Pick the right skill for the goal:

Audit (findings; responsive may then fix)

audit-responsive — linearized mobile layout at every breakpoint; desktop is not a wide phone. Prefer /responsive-audit when that is the symptom. Audit-and-fix.
audit-ui-states — empty / loading / error / offline / overflow matrix. Read-only.
audit-uiux-design-system — token compliance, component modularity, design drift.
audit-ux — per-page NN/g heuristics and microcopy. Not cross-page flows.
audit-ux-journeys — cross-page stories, IA, findability.
audit-accessibility — WCAG 2.2 / axe / keyboard.

Plan vs apply-now cleanup

plan-uiux-unification — full UI/UX + design-system burndown. No code until approved.
housekeep-design — apply-now SSOT migration after an approved plan (or explicit "clean it up now").

Enhance (apply)

enhance-readability — understood (CPL, Gestalt grouping, deadspace, visuals that cut verbosity). Prefer /readability when that is the symptom.
enhance-web-instant-nav — Speculation Rules, bfcache, View Transitions, 103 Early Hints. Prefer /instant-nav when the first page is fast and the next is slow.
enhance-web-ui — composition, hierarchy, spacing, type on an existing product page.
enhance-web-ux — flows and semantic data wiring; "this page feels AI-generated".
enhance-web-landing — marketing / portfolio greenfield.
enhance-web-redesign — existing-site upgrade, preserve behavior.
enhance-web-web3d — WebGL / cinematic scroll on an existing site.
enhance-web-forms — production-quality forms.
enhance-motion — coherent motion pass across an existing app.
design-motion — one new isolated animation.
mobile-rn-screen — React Native screen (Expo / bare).
enhance-capacitor-ui — Capacitor / hybrid shell, then the web or RN skill.
enhance-readme — repo README showcase.

Native iOS/Android (SwiftUI / Compose, no web layer) is out of scope — use Apple HIG / Material directly.

Use /uiux to explicitly trigger UI/UX work. Otherwise, describe the symptom and the right skill auto-fires.

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.

2d ago First seen · 45 lines · 24 tokens per session scan A f1a0aed5e8e3

Subscribe to this mod's changes

uiux is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 8d ago), licensed MIT. It adds 24 tokens to every session and 651 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 2026-09-03.

CSS and styling Design and UX Frontend agent-skills ai-agent claude claude-skills cursor cursor-ai

ux-system

Propose a complete starter design system for a project that doesn't have one. Triggers on "we don't have a design system", "build us a system", "propose tokens", "what should our theme be". Use when proposing a starter design system, generating tokens / foundations / components from a brand brief, the project has no…

Laith0003/ux-skill · 102 tokens

ux-image-to-code

Take a design reference image (PNG/JPG/WebP), extract its dominant palette + canvas polarity + type signal via pure Pillow CV, match the result against the v2 palettes/styles manifests, and run the recommender on the synthetic brief. Returns the closest palette, the closest style, and a full recommended design system…

Laith0003/ux-skill · 76 tokens

ux-recommend

The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…

Laith0003/ux-skill · 93 tokens

uiux