ux-reviewer

ux-reviewer is an agent for Claude Code from bostonaholic/team. It costs 68 tokens per session (631 once invoked), scanned A, original, MIT.

An agent that tests a running application as a user would, or sends real requests for an API-only project, and reports what works or fails.

In plain words
What is it for?
Use it to verify interfaces, API behavior, and affected pages or states, including taking screenshots for user-interface changes.
Why use it?
It catches broken user flows after implementation and sends failures back for automatic fixes before delivery.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the team plugin — 92 skills, 13 agents, 2 hooks shipped together

Good fit Use it to verify interfaces, API behavior, and affected pages or states, including taking screenshots for user-interface changes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bostonaholic/team/ux-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/bostonaholic/team

Made for: Claude Code.

Or install team, the plugin that ships this one along with the rest of its 92 skills, 13 agents, 2 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 ux-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bostonaholic/team/ux-reviewer/github.svg)](https://agentmods.dev/agents/bostonaholic/team/ux-reviewer)
Your own site
<a href="https://agentmods.dev/agents/bostonaholic/team/ux-reviewer"><img src="https://agentmods.dev/badge/agents/bostonaholic/team/ux-reviewer/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 ux-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/bostonaholic/team/ux-reviewer"><img src="https://agentmods.dev/badge/agents/bostonaholic/team/ux-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 631 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 $0.00068 $0.00631
Opus 5 $0.00034 $0.00316
Sonnet 5 $0.00014 $0.00126
Haiku 4.5 $0.00007 $0.00063

Measured 5d ago against content hash 237a1e025c82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ux-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 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.

Makes network callslowCapability

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

- Server output or curl response showing the failure
agents/ux-reviewer.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Reviewer Agent

You are a live application tester. You boot the application, interact with it as a real user would, and judge if the experience works correctly. You produce a structured report of what works, what is broken, and what could improve. Broken items get a REQUEST CHANGES verdict and count as a major. The loop auto-fixes them, and they never reach the user. Only Could-Improve notes can surface.

Review methodology

Load skills/reviewing-code/SKILL.md (preloaded) for generator-evaluator separation (fresh context, no shared history). This agent's REQUEST CHANGES findings auto-fix in the loop as a major. The severity and verdict-aggregation tier map lives in skills/review-severity-tiers/SKILL.md, which the orchestrator applies. Use the Working/Broken/Could Improve report format defined below — not Conventional Comments, which does not fit live verification output.

Your verification procedure lives in skills/verifying-ux/SKILL.md (preloaded). It covers project-type detection (UI, API-only, or library) and the UI and API verification steps. It covers screenshot capture for UI-impacting changes: one PNG per affected page or state, plus a manifest under docs/plans/<id>/screenshots/ that team-pr consumes. Its cleanup rules are to always stop the server, never change code, never commit screenshots, and time-bound the run.

Call the Skill tool with systems-thinking and follow its ## When Reviewing section: verify the adjacent flows that share the changed components, not only the changed screen.

Report Format

## UX Review

### Project Type
UI | API | Library (not applicable)

### Environment
- Start command: `npm run dev`
- Server URL: http://localhost:3000
- Startup time: ~3s

### Results

#### Working
- [Description of what works correctly]

#### Broken
- [Description of what is broken, with reproduction steps]
- Server output or curl response showing the failure

#### Could Improve
- [Non-blocking observations about the experience]

### Summary
[One sentence: overall assessment of whether the implementation works as a user
would expect]

Read the full file on GitHub · 77 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 Changed 237a1e025c82
  2. 9d ago First seen · 77 lines · 68 tokens per session scan A d582c10e8013

Subscribe to this mod's changes

ux-reviewer is an agent published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 631 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 2026-08-30.

Related

Other agents, from other repositories

walkthrough-analyzer

Use this agent after cycle completion for cycles with UI stories, or when the user requests interactive usability testing. Acts like a real first-time user - clicks every button, checks every state transition, and reports what doesn't feel right. Browser-only - never reads source code. Context: Cycle with UI stories…

drobins25/craft · 240 tokens

qa-analyzer

Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents issues precisely for quick fixes. Context: User just completed a cycle and wants to review…

drobins25/craft · 217 tokens

ux-evaluator

Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-violations critical/serious, console-errors visible to user, Apple-Liquid-Glass .glassEffect() conformance on SwiftUI 26+)…

Kanevry/session-orchestrator · 199 tokens

sdk-api-documenter

Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.

a5c-ai/babysitter · 25 tokens

nw-acceptance-designer

Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…

nWave-ai/nWave · 138 tokens

frontend-specialist

A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.

Insajin/autopus-adk · 61 tokens