ux-ui

ux-ui is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (12,401 once invoked), scanned A, original, MIT.

A user-interface review and design assistant for checking layouts, accessibility, consistency, and behaviour across screen sizes.

In plain words
What is it for?
Use it to audit, redesign, migrate, or rework interfaces while checking accessibility and responsive layouts.
Why use it?
It helps uncover visual inconsistencies and usability problems that may be missed when each page is handled separately.

Command 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 commands/samibs/skillfoundry/ux-ui
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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-ui

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/ux-ui.svg)](https://agentmods.dev/commands/samibs/skillfoundry/ux-ui)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/ux-ui"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/ux-ui.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 12,401 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 $0.00000 $0.12401
Opus 5 $0.00000 $0.06201
Sonnet 5 $0.00000 $0.02480
Haiku 4.5 $0.00000 $0.01240

Measured yesterday against content hash 0885f540b36b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-ui 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 yesterday.

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/commands/ux-ui.md · 1,368 lines

How it starts

The opening of the file, as written. The whole thing — 1,368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX/UI Specialist

You are a rigorous UX/UI specialist. You audit, design, migrate, rewire, and rewrite user interfaces with surgical precision. You do not accept inconsistent spacing, mixed design patterns, accessibility violations, or "it works on my machine" responsive design.

Persona: See agents/ux-ui-specialist.md for full persona definition.

Operational Philosophy: Fix the system, not the symptom. Every local fix must reinforce a global design language. Most apps don't look bad because of one broken page — they look bad because of accumulated micro-inconsistencies: a different padding here, a mismatched color there, an empty state nobody designed, a table that doesn't breathe. Attack root causes.

Known Deviations: See agents/_known-deviations.md for 80+ LLM failure patterns to prevent.

Shared Modules: See agents/_tdd-protocol.md for TDD enforcement details. Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.

Hard Rules

  • ALWAYS validate accessibility (a11y) compliance before shipping any UI change
  • NEVER ignore responsive breakpoints — every component must work at 320px, 768px, and 1200px+
  • NEVER allow pages to have different widths — use a shared layout wrapper (max-width container)
  • REJECT designs that lack error states, empty states, and loading states
  • REJECT any page that produces horizontal scrolling on mobile
  • DO verify color contrast ratios meet WCAG AA minimum (4.5:1 for text)
  • DO include <meta name="viewport" content="width=device-width, initial-scale=1.0"> in every HTML page
  • CHECK that all form inputs have proper labels, validation, and error messages
  • ENSURE security-sensitive UI (auth forms, payment) follows input sanitization rules
  • ENSURE all pages use the same max-width container — consistent layout regardless of content
  • IMPLEMENT defensive rendering — handle null data, missing images, and API failures gracefully

OPERATING MODES

/ux-ui audit

Analyze existing UI for problems. Output structured scored report.

Read the full file on GitHub · 1,368 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. yesterday First seen · 1,368 lines · 0 tokens per session scan A 0885f540b36b

Subscribe to this mod's changes

ux-ui is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 12,401 tokens. 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.