frontend-review

frontend-review is a command for Claude Code from oalders/kitchen-sink. It costs 14 tokens per session (2,581 once invoked), scanned A, original, MIT.

A review command for frontend changes, including HTML, CSS, images, and interface components. It checks accessibility, responsive behavior across screen sizes, visual regressions, image handling, and CSS patterns.

In plain words
What is it for?
Use it when changing page structure, styles, images, templates, or components, especially before treating a visual change as ready for production.
Why use it?
It helps catch user-facing problems such as inaccessible content, broken mobile layouts, inefficient images, and unexpected visual changes.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the kitchen-sink plugin — 9 skills, 20 commands, 12 hooks shipped together

Good fit Use it when changing page structure, styles, images, templates, or components, especially before treating a visual change as ready for production.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/oalders/kitchen-sink/frontend-review
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/oalders/kitchen-sink

Made for: Claude Code.

Or install kitchen-sink, the plugin that ships this one along with the rest of its 9 skills, 20 commands, 12 hooks.

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 frontend-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/oalders/kitchen-sink/frontend-review/github.svg)](https://agentmods.dev/commands/oalders/kitchen-sink/frontend-review)
Your own site
<a href="https://agentmods.dev/commands/oalders/kitchen-sink/frontend-review"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/frontend-review/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 frontend-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/oalders/kitchen-sink/frontend-review"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/frontend-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,581 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 $0.00014 $0.02581
Opus 5 $0.00007 $0.01290
Sonnet 5 $0.00003 $0.00516
Haiku 4.5 $0.00001 $0.00258

Measured 10d ago against content hash 9ad02240cecc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

frontend-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 10d 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.

commands/frontend-review.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Review

Overview

Frontend-focused code review for HTML/CSS/image changes, emphasizing: (1) Image optimization and accessibility, (2) Responsive design across viewports, (3) Visual regression, (4) CSS best practices. Spawns general-purpose subagent.

When to Use

Use when:

  • Converting image formats (JPEG → SVG, PNG → WebP, etc.)
  • Changing CSS styles or layouts
  • Updating HTML templates or components
  • Making visual/UI changes

Don't use when:

  • Pure backend code changes
  • No visual/UI impact

Steps

1. Get Git SHAs

Check conversation context first. If not available:

git rev-parse origin/main
git rev-parse HEAD

2. Invoke Frontend-Focused Code Reviewer

Task(general-purpose):
  description: Frontend review of [feature]
  model: "sonnet"

  prompt:
    # Frontend Code Review Agent

    You are a frontend expert reviewing code for images, accessibility, responsive design, and CSS best practices.

    **Your task:**
    1. Review frontend code changes
    2. Apply systematic frontend checklist
    3. Verify accessibility (ARIA, semantic HTML)
    4. Check responsive design and visual quality
    5. Assess production readiness

    ## What to Review

    [Brief summary - e.g., "SVG logo conversion with CSS updates"]

    ## Requirements/Plan

    [Issue details or requirements]

    ## Git Range to Review

    ```bash
    git diff --stat BASE_SHA..HEAD_SHA
    git diff BASE_SHA..HEAD_SHA
    ```

    ## Frontend Review Checklist

    **CRITICAL: Check EVERY category systematically.**

    ### Images & Assets

    **SVG Optimization:**
    - SVG has proper structure (viewBox, no hard-coded width/height)?
    - SVG optimized (run through SVGO)?
    - SVG uses semantic elements (title, desc)?
    - SVG color strategy (currentColor vs hard-coded)?
    - File size improvement vs previous format?

    **Image Accessibility:**
    - Alt text descriptive and meaningful (not just "Logo" or "Image")?
    - Decorative images have `alt=""` or `aria-hidden="true"`?
    - Informative images have proper alt text?
    - SVGs used as images have `role="img"`?
    - Complex graphics have longer descriptions (aria-describedby)?

    **Image Performance:**
    - Appropriate format (SVG for logos/icons, WebP for photos)?
    - Images compressed/optimized?
    - Lazy loading for below-fold images?
    - Preload hints for critical images (hero, logo)?
    - Responsive images (srcset, picture) where needed?

    ### ARIA & Semantic HTML

    **ARIA Labeling Strategy:**
    - Is element decorative or informative?
    - If decorative: `aria-hidden="true"` and no alt text
    - If informative: meaningful alt text or aria-label
    - Redundant ARIA avoided (img alt + SVG title)?
    - Parent links/buttons have accessible names?

    **Example ARIA decisions:**
    ```html
    <!-- ❌ BAD: Redundant labels -->
    <a href="/" aria-label="Home">
      <img src="logo.svg" alt="My Company Logo">
    </a>

Read the full file on GitHub · 348 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. 10d ago First seen · 348 lines · 14 tokens per session scan A 9ad02240cecc

Subscribe to this mod's changes

frontend-review is a command published in the GitHub repository oalders/kitchen-sink (4 stars, last pushed 10d ago), licensed MIT. It adds 14 tokens to every session and 2,581 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.