kiro-rails: Command for Claude Code

.claude/commands/review-ux-audit.md

review-ux-audit is a command for Claude Code from sourjya/kiro-rails. It costs 36 tokens per session (2,344 once invoked), scanned A, original, MIT.

A review of a frontend codebase from the perspective of its users, covering how people navigate the product and complete tasks.

In plain words
What is it for?
Use it to create user profiles, task journeys, heuristic findings, and a prioritized list of fixes; the product type and main user goal must be supplied.
Why use it?
It finds confusing journeys, inconsistent interfaces, and usability problems that may not be obvious from individual components or screens.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is sourjya/kiro-rails's own configuration. It tells Claude Code how to work on kiro-rails itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kiro-rails configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sourjya/kiro-rails. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sourjya/kiro-rails/main/.claude/commands/review-ux-audit.md
Clone the repo
git clone --depth 1 https://github.com/sourjya/kiro-rails

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 review-ux-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/sourjya/kiro-rails/review-ux-audit/github.svg)](https://agentmods.dev/commands/sourjya/kiro-rails/review-ux-audit)
Your own site
<a href="https://agentmods.dev/commands/sourjya/kiro-rails/review-ux-audit"><img src="https://agentmods.dev/badge/commands/sourjya/kiro-rails/review-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.

agentmods 80×15 button for review-ux-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/sourjya/kiro-rails/review-ux-audit"><img src="https://agentmods.dev/badge/commands/sourjya/kiro-rails/review-ux-audit.svg" alt="Reviewed on agentmods" width="80" 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 2,344 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.02344
Opus 5 $0.00018 $0.01172
Sonnet 5 $0.00007 $0.00469
Haiku 4.5 $0.00004 $0.00234

Measured 11d ago against content hash 9dc124ce9d5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-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 11d 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/commands/review-ux-audit.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Audit - Frontend Codebase Review

Before scanning, read docs/decisions/ ADRs and any UX/design documentation if they exist. Use documented UX decisions to distinguish intentional pattern choices from accidental inconsistency.

Input block (fill before running)

PRODUCT_TYPE: [Required - e.g. SaaS dashboard, developer tool, admin panel] PRIMARY_USER_GOAL: [Required - one sentence, what the main user came to do] TECH_STACK: [Optional - framework, state management, component library] KNOWN_PAIN_POINTS: [Optional - existing complaints or known issues] AUDIT_SCOPE: [Optional - limit to specific routes or personas] OUT_OF_SCOPE: [Optional - anything explicitly excluded]

If PRODUCT_TYPE and PRIMARY_USER_GOAL are not provided, ask for them before proceeding. Do not infer these from the codebase.


Role

You are a senior UX engineer and frontend code reviewer. You hold two concurrent lenses:

  • Primary lens: An experienced product designer who reads code as a proxy for user experience - routes as navigation, components as affordances, state management as memory, loading states as feedback.
  • Secondary lens: A first-time user of this exact product type, walking through the interface with no prior knowledge and no patience for friction.

Core principles you apply throughout:

  • User Experience Patterns: Progressive disclosure, information hierarchy, cognitive load reduction, error prevention over recovery, recognition over recall
  • Accessibility: WCAG 2.2 AA minimum, keyboard operability, screen reader support, sufficient contrast, reduced motion support
  • Usability: Nielsen heuristics, Fitts's law, Hick's law, learnability, efficiency, trust
  • Content Design: Plain language, action-oriented labels, consistent terminology

State coverage - always consider: Default, Empty, Loading, Success, Warning, Error, Permission-restricted, Edge cases.

You do not guess. You do not speculate about what a component might do. You READ the file first. If you cannot confirm a behavior from the code, flag it as "unverifiable without runtime data" and move on.

Read the full file on GitHub · 277 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. 11d ago First seen · 277 lines · 36 tokens per session scan A 9dc124ce9d5d

Subscribe to this mod's changes

review-ux-audit is a command published in the GitHub repository sourjya/kiro-rails (9 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,344 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 2026-08-31.