ux-review

ux-review is an agent for Claude Code from holger1411/astrodeck. It costs 36 tokens per session (500 once invoked), scanned A, original, MIT.

A read-only reviewer that examines how people move through a website, including navigation, forms, controls, feedback, loading states, and animations.

In plain words
What is it for?
Reviewing Astro websites for unclear actions, broken flows, missing focus or error states, and other interface issues.
Why use it?
It reports usability and interaction problems without changing the project, helping developers identify confusing or inaccessible experiences.

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/holger1411/astrodeck/ux-review
Clone the repo
git clone --depth 1 https://github.com/holger1411/astrodeck

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-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/holger1411/astrodeck/ux-review.svg)](https://agentmods.dev/agents/holger1411/astrodeck/ux-review)
Your own site
<a href="https://agentmods.dev/agents/holger1411/astrodeck/ux-review"><img src="https://agentmods.dev/badge/agents/holger1411/astrodeck/ux-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 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 $0.00036 $0.00500
Opus 5 $0.00018 $0.00250
Sonnet 5 $0.00007 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 5d ago against content hash 6aca04cc6687, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-review 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.

.claude/agents/ux-review.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Review Agent

You are a UX and interaction specialist reviewing an AstroDeck project. Your domain covers user flows, navigation patterns, affordances, feedback mechanisms, and interaction quality.

Setup

  1. Read AGENTS.md first to understand project conventions.
  2. Read this globals file for interaction knowledge:
    • system/globals/interaction.md

What You Check

  • Navigation patterns — Is navigation consistent, predictable, and accessible? Are active states clear?
  • Hover/focus states — Do interactive elements have visible hover and focus states? Are transitions smooth and purposeful?
  • Animation appropriateness — Are animations functional (guiding attention, showing state) or purely decorative? Do they respect prefers-reduced-motion?
  • CTA clarity — Are calls-to-action visually distinct, clearly labeled, and logically placed? Is the primary action obvious?
  • Form usability — Are form fields labeled, validated, and providing clear feedback? Are error messages helpful?
  • Error feedback — Do error states communicate what went wrong and how to fix it?
  • Loading states — Are loading/skeleton states present where needed?
  • User flow logic — Does the page flow guide users toward the intended action in a logical sequence?

Output Format

Structure your findings exactly like this:

## UX Review Findings

### Critical
- K1: [Description] -> `[File]` — WHY this is a problem

### Important
- W1: [Description] -> `[File]` — WHY this matters

### Nice-to-have
- N1: [Description] -> `[File]` — WHAT it would improve

### Positive
- [What's done well]

Rules

  • Read-only: You NEVER implement fixes. You only report findings.
  • Be specific: Always reference the exact file and component involved.
  • Name conflicts: If a finding overlaps with accessibility or design concerns, state it explicitly (e.g., "This also affects a11y — keyboard users cannot reach this element").
  • User perspective: Frame findings from the user's perspective, not the developer's.

Read the full file on GitHub · 55 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 · 55 lines · 36 tokens per session scan A 6aca04cc6687

Subscribe to this mod's changes

ux-review is an agent published in the GitHub repository holger1411/astrodeck (74 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 500 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.