component-reviewer

component-reviewer is an agent for Claude Code from Aboudjem/ui-ux-suite. It costs 15 tokens per session (873 once invoked), scanned A, original, MIT.

An agent that reviews interface components for consistent patterns and complete interaction states. Interaction states are appearances such as hover, keyboard focus, loading, disabled, error, and empty.

In plain words
What is it for?
Use it to audit buttons, inputs, cards, tables, and other components for state coverage, visual consistency, accessibility, and reusable patterns.
Why use it?
It exposes missing states and inconsistent behaviours that can confuse users or leave components unusable during real interactions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ui-ux-suite plugin — 14 skills, 5 commands, 12 agents, 1 MCP server shipped together

Good fit Use it to audit buttons, inputs, cards, tables, and other components for…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aboudjem/ui-ux-suite/component-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/Aboudjem/ui-ux-suite

Made for: Claude Code.

Or install ui-ux-suite, the plugin that ships this one along with the rest of its 14 skills, 5 commands, 12 agents, 1 MCP server.

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 component-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aboudjem/ui-ux-suite/component-reviewer.svg)](https://agentmods.dev/agents/aboudjem/ui-ux-suite/component-reviewer)
Your own site
<a href="https://agentmods.dev/agents/aboudjem/ui-ux-suite/component-reviewer"><img src="https://agentmods.dev/badge/agents/aboudjem/ui-ux-suite/component-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 873 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 $0.00015 $0.00873
Opus 5 $0.00008 $0.00436
Sonnet 5 $0.00003 $0.00175
Haiku 4.5 $0.00002 $0.00087

Measured 7d ago against content hash ddcb95e30f99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

component-reviewer 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 7d 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.

agents/component-reviewer.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Component Reviewer

You audit UI component quality, consistency, and pattern adherence.

Required Reading

Before reviewing components, read these knowledge files:

  • knowledge/component-patterns.md - State checklists, button hierarchy, form best practices
  • knowledge/libraries-tools.md - Component library comparison and best-in-class patterns
  • knowledge/wow-libraries-2026.md - 15 component libraries deep-dived for current best practices

Use the Read tool to load each file. Apply this knowledge when scoring and recommending.

What you evaluate

1. State Coverage (weight: 30%)

Every interactive component should handle these states:

  • default - resting state
  • hover - mouse over (desktop)
  • active/pressed - being clicked/tapped
  • focus/focus-visible - keyboard focus
  • disabled - not interactive
  • loading - performing action
  • error - something went wrong
  • empty - no data/content
  • skeleton - loading placeholder

Check for each component type:

  • Buttons: default, hover, active, focus, disabled, loading
  • Inputs: default, hover, focus, filled, error, disabled, readonly
  • Cards: default, hover (if clickable), selected, skeleton
  • Tables: default, loading, empty, error, sorting, selected rows
  • Modals: open, closing animation, focus trap active

2. Button Hierarchy (weight: 15%)

  • Is there a clear primary/secondary/ghost/destructive hierarchy?
  • Is there only ONE primary action per section?
  • Are destructive actions visually distinct (red/danger color)?
  • Do buttons have consistent sizing (sm/md/lg)?
  • Icon-only buttons: do they have aria-label?

3. Form Quality (weight: 20%)

  • Labels: visible labels (not placeholder-only)?
  • Validation: inline, real-time (debounced), or on submit?
  • Error messages: say what to fix, not just "invalid"?
  • Help text: available for complex fields?
  • Required/optional: clearly marked?
  • Autocomplete attributes: present for common fields?
  • Input types: email, tel, url, number used appropriately?

Read the full file on GitHub · 91 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. 7d ago First seen · 91 lines · 15 tokens per session scan A ddcb95e30f99

Subscribe to this mod's changes

component-reviewer is an agent published in the GitHub repository Aboudjem/ui-ux-suite (7 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 873 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 2026-08-31.

Related

Other agents, from other repositories

ui-designer

Designs a screen, flow, or component from a brief — establishing hierarchy, layout, tokens, states, and motion before (or instead of) writing code. Use when the user wants design direction, a structured spec, or a thoughtfully composed interface rather than just raw code. Pairs with the frontend-implementer agent for…

ca-who-codes/ultimate.UIUX.design.skills · 73 tokens

design-reviewer

Rigorously audits an existing UI (code, screenshot, or live page) against the UI/UX Design Pro knowledge base and returns prioritized, specific findings. Use when the user asks to "review", "critique", "audit", or "improve" an interface, or before shipping. Defaults to finding concrete issues — vague praise is a…

ca-who-codes/ultimate.UIUX.design.skills · 76 tokens

visual-designer

Designs and produces fixed-canvas visual & marketing collateral — presentations/decks, social carousels and posts, ads, A4/A3 posters, flyers, brochures, business cards, event banners/signage, email/newsletters, infographics, and brand kits. Use when the user wants a deck, carousel, creative, poster, or email — not an…

ca-who-codes/ultimate.UIUX.design.skills · 99 tokens

frontend-implementer

Builds production-quality, accessible UI code from a design or brief using the recommended modern stack (React + TypeScript + Tailwind v4 + shadcn/ui + Radix + Motion). Use when the user wants the actual component/page code, not just design direction. Produces clean, typed, accessible, state-complete components.

ca-who-codes/ultimate.UIUX.design.skills · 73 tokens

frontend-designer

Use this agent when you need to convert design mockups, wireframes, or visual concepts into detailed technical specifications and implementation guides for frontend development. This includes analyzing UI/UX designs, creating design systems, generating component architectures, and producing comprehensive documentation…

andisab/swe-marketplace · 356 tokens

design-reviewer

Use to audit UI code (SwiftUI, UIKit, AppKit, React/React Native, Flutter, HTML/CSS, etc.) against Apple's Human Interface Guidelines and report concrete violations. Invoke when the user asks to review/check/audit a screen, view, component, or stylesheet for HIG compliance, accessibility, or design-token correctness …

Elevatormusic/apple-hig · 102 tokens