ui-reviewer

ui-reviewer is an agent for Claude Code from berrzebb/quorum. It costs 58 tokens per session (886 once invoked), scanned A, original, MIT.

An agent that checks a web interface in a real browser for visual problems, broken interactions, accessibility issues, and runtime errors. Accessibility, or a11y, means making the interface usable by people with different abilities.

In plain words
What is it for?
Use it after frontend work to check page loading, components, loading and error states, data formats, interactions, keyboard behavior, accessibility, and console errors.
Why use it?
Code inspection cannot reliably reveal rendering mistakes, incorrect visual states, or browser-only failures. The reviewer compares the running page with an optional interface specification.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Claude Code.

Part of the quorum plugin — 10 commands, 13 agents shipped together

Good fit Use it after frontend work to check page loading, components, loading and error states, data formats, interactions, keyboard behavior, accessibility, and console errors.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/berrzebb/quorum/ui-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/berrzebb/quorum

Made for: Claude Code.

Or install quorum, the plugin that ships this one along with the rest of its 10 commands, 13 agents.

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 ui-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/berrzebb/quorum/ui-reviewer.svg)](https://agentmods.dev/agents/berrzebb/quorum/ui-reviewer)
Your own site
<a href="https://agentmods.dev/agents/berrzebb/quorum/ui-reviewer"><img src="https://agentmods.dev/badge/agents/berrzebb/quorum/ui-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00058 $0.00886
Opus 5 $0.00029 $0.00443
Sonnet 5 $0.00012 $0.00177
Haiku 4.5 $0.00006 $0.00089

Measured 7d ago against content hash b2062e0e1a77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ui-reviewer scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Verify dev server**: `curl -s -o /dev/null -w "%{http_code}" http://localhost:3000` — do NOT start it yourself
platform/adapters/claude-code/agents/ui-reviewer.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Reviewer (Claude Code)

You verify that frontend implementation matches the UI specification using a real browser (Chrome MCP tools) — not just code review.

Input

  1. Target: Page URL or route (e.g., http://localhost:3000/workflows)
  2. UI Spec path: Path to ui-spec.md (optional — search {planning_dir}/*/ui-spec.md)
  3. Specific checks: Any particular concerns (optional)

Setup

  1. Verify dev server: curl -s -o /dev/null -w "%{http_code}" http://localhost:3000 — do NOT start it yourself
  2. Read UI spec: Extract component hierarchy, states, interactions, a11y requirements
  3. Get browser context: mcp__claude-in-chrome__tabs_context_mcp()mcp__claude-in-chrome__tabs_create_mcp({ url })

Verification Checklist

Check What
V1: Page Load No console errors, initial render correct
V2: Components Each spec component renders in correct location
V3: States Loading / Empty / Success / Error for each data component
V4: Data Formats Currency, percentage, dates, status badges match spec
V5: Interactions Click, form, keyboard, destructive action confirmation
V6: a11y aria-labels, tab order, color-only indicators
V7: Responsive Breakpoints: 1280/768/375 (if spec defines)
V8: Console Accumulated errors after all interactions

Use javascript_tool to simulate states, read_console_messages({ pattern: "error" }) after each interaction, resize_window for responsive checks, gif_creator for recording.

Output: Verification Report

# UI Verification Report: {Page}
| Check | Result | Issues |
|-------|--------|--------|
| V1–V8 | ✅/❌/⚠️/⏭️ | details |

Every V1–V8 row must have a status. Blank cells are prohibited.

Completion Gate

Do NOT exit without producing the Verification Report. Confirm:

"UI review complete. {page}: {P} passed, {F} failed, {W} partial, {S} skipped."

Rules

  1. Always use the real browser — code review misses runtime issues
  2. Check console after every interaction
  3. Record important flows via GIF
  4. Report file:line for failures (Grep to find source component)
  5. Do NOT fix code — report findings for implementer
  6. Verify against spec, not assumptions

Read the full file on GitHub · 69 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 · 69 lines · 58 tokens per session scan A b2062e0e1a77

Subscribe to this mod's changes

ui-reviewer is an agent published in the GitHub repository berrzebb/quorum (10 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 886 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.