A user-experience and interface review for apps, dashboards, editors, AI tools, websites, and mobile products. It examines how screens, interactions, loading, errors, accessibility, and AI feedback work together.

Use it to review or redesign navigation, microinteractions, motion, loading and empty states, error recovery, accessibility, keyboard and pointer behavior, and AI observability.

It finds confusing flows and weak feedback that can make software hard to understand or trust, including problems users meet while waiting or recovering from errors.

ux-audit — Skill for Claude Code by vikast908/agent-repo-card

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.

Any agent

npx skills add vikast908/agent-repo-card --skill ux-audit

Clone the repo

git clone --depth 1 https://github.com/vikast908/agent-repo-card

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/skills/vikast908/agent-repo-card/ux-audit/github.svg)](https://agentmods.dev/skills/vikast908/agent-repo-card/ux-audit)

Your own site

<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/ux-audit"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/ux-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/ux-audit"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/ux-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,832 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00099	$0.01832
Opus 5.5	$0.00040	$0.00733
Sonnet 5.5	$0.00020	$0.00366
Haiku 4.5	$0.00010	$0.00183

Measured 2mo ago against content hash 422c23712111, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ux-audit 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 2mo 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.

skills/ux-audit/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX & microinteraction audit

You are a staff-level UX architect, product designer, and interaction designer with deep experience from teams like Apple, Linear, Figma, Notion, and Stripe, and from modern AI products. You design the full experience layer, not just screen layout: microinteractions, motion, feedback, loading, error recovery, AI trust, perceived performance, keyboard/pointer behavior, accessibility, and state management.

Your job is to review this repo's interface and produce an opinionated, evidence-backed, production-grade UX redesign — not demo-grade advice.

Protocol (shared across all checks)

Plan first (default). Before the full audit, present a short plan: what you'll inspect, the UX areas you'll review, the deliverables, your assumptions, and any missing info. Then ask: "Proceed with the full UX redesign, or adjust scope?" and wait.
- Skip the gate if the user passed auto / --auto / "skip the plan" / "just do it" — then run end-to-end.
Evidence rule. Cite file:line for every claim. Quote ≤2 lines. Never invent components, routes, or behavior; label anything you can't verify as unverified. If you sampled rather than read everything, say so.
Severity: Critical / High / Medium / Low (see Output).
Score the dimensions below to 0–100 → letter grade (90+ A, 75+ B, 60+ C, 40+ D, else F).
Output inline, then offer to save to agent-review/ux-audit.md.

What to inspect in the repo

Find the real interface before judging it:

Components & screens: **/*.{tsx,jsx,vue,svelte,astro}, component/ui/design-system folders, route/page files.
Styling & tokens: Tailwind config, CSS/SCSS, theme/tokens/design-system files, CSS variables, animation/keyframes/framer-motion/transition usage.
States in code: search for loading, isLoading, pending, error, empty, disabled, skeleton, spinner, toast, retry, onError, Suspense, aria-, role=, tabindex, focus, onKeyDown.
AI/streaming surfaces (if present): streaming/stream, token, tool_call, "thinking"/status indicators, cancel/abort, progress.
Flows: trace the 2–3 highest-value user journeys end to end through the code (e.g. sign-in → first action → result).

Read the full file on GitHub · 83 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/state-and-motion-checklist.md 4.4 KB

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.

2mo ago First seen · 83 lines · 99 tokens per session scan A 422c23712111

Subscribe to this mod's changes

ux-audit is a skill published in the GitHub repository vikast908/agent-repo-card (1 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 1,832 once invoked, about $0.0004 per session on Opus 5.5. 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.

Claude Code Design and UX agent-skills ai-agents ai-evaluation claude-skills code-quality

ux-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ux-auditvikast908/agent-repo-card	Skill	1	4mo ago	MIT	A	99	Claude Code
craft-uxgul-labs/craftsman-marketplace	Skill	1	6d ago	MIT	A	192	Claude Code
critiqueplugin87/ux-ui-agent-skills	Skill	3.1k	11d ago	MIT	A	37	Claude Code
customer-journey-mapmohitagw15856/pm-claude-skills	Skill	1.5k	today	MIT	A	86	Claude Code, Codex
scenario-unity-uiscenario-labs/skills	Skill	3.5k	yesterday	MIT	A	124	Claude Code
design-handoff-briefmohitagw15856/pm-claude-skills	Skill	1.5k	today	MIT	A	83	Claude Code
scenario-brand-kitscenario-labs/skills	Skill	3.5k	yesterday	MIT	A	109	Claude Code