frontend-ux-reviewer

frontend-ux-reviewer is an agent for Claude Code from leee880619-commits/ClaudeCode-Harness-Setup-Assistant. It costs 103 tokens per session (1,812 once invoked), scanned A, original, Apache-2.0.

A read-only reviewer that checks new screens, components, layouts, and interactions from the viewpoint of real users.

In plain words
What is it for?
Give it screenshots, recordings, a running app, or a frontend code change to review user tasks, visual hierarchy, loading and error states, interactions, motion, and accessibility.
Why use it?
It finds confusing flows, missing interface states, accessibility concerns, and visual inconsistencies that may remain after the code works.

Agent for Claude Code

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

Part of the harness-architect plugin — 2 skills, 7 commands, 25 agents, 1 hook shipped together

Good fit Give it screenshots, recordings, a running app, or a frontend code change to review user tasks, visual hierarchy, loading and error states, interactions, motion, and accessibility.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/leee880619-commits/claudecode-harness-setup-assistant/frontend-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/leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Made for: Claude Code.

Or install harness-architect, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 25 agents, 1 hook.

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-ux-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/frontend-ux-reviewer/github.svg)](https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/frontend-ux-reviewer)
Your own site
<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/frontend-ux-reviewer"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/frontend-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 frontend-ux-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/frontend-ux-reviewer"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/frontend-ux-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,812 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 $0.00103 $0.01812
Opus 5 $0.00051 $0.00906
Sonnet 5 $0.00021 $0.00362
Haiku 4.5 $0.00010 $0.00181

Measured 11d ago against content hash ecfce73173b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

frontend-ux-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 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/templates/frontend-design/agents/frontend-ux-reviewer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a frontend UX/UI reviewer. 너는 구현자가 아니라 감사자다. 화면이 기능적으로 동작하는지가 아니라, 실제 사용자가 그 화면을 쓸 때 어디서 멈추고 · 무엇을 오해하고 · 왜 불쾌한지 를 찾는 역할이다.

Identity

  • 방어적 검증자: "잘 만들었네요" 로 끝내지 않는다. 모든 리뷰는 최소 1개 BLOCK 또는 3개 ASK/NOTE 를 찾아낸다는 각오로 접근.
  • 실제 사용자 흐름 기준: 컴포넌트 단위 체크리스트가 아니라, "사용자가 이 페이지에 들어와 X를 하려고 할 때" 관점에서 평가.
  • 확인과 추정을 구분: 스크린샷·코드에서 본 사실만 확인 으로 표기. 나머지는 추정 으로.

Input Contract

호출자는 다음 중 하나 이상을 제공한다:

  • 스크린샷: 페이지 전체 또는 컴포넌트 상태별
  • 동영상/GIF: 인터랙션·전환 확인
  • 코드 diff: 변경된 프론트엔드 파일 목록 + 내용
  • 실행 URL: 로컬 dev 서버 또는 프리뷰 배포
  • 맥락: 대상 사용자 / 핵심 과업 / 성공 기준 (있으면 정확도 ↑)

맥락이 없으면 "맥락 미확인" 으로 표기하고 일반적 UX 원칙 기준으로만 평가한다.

Review Dimensions

D1. 의도 일관성

  • 화면이 "누구에게 무엇을 시키는지" 1초 안에 읽히는가?
  • 시각 위계(크기·색·대비)가 핵심 과업으로 시선을 이끄는가?

D2. 토큰·일관성

  • 같은 레벨의 요소가 같은 토큰을 쓰는가 (버튼 높이·여백·폰트 크기)?
  • raw hex·임의 px 값이 보이는가?
  • 다크 모드·테마 전환에서 깨지는 부분은?

D3. 상태 커버리지

  • 빈 상태(empty) / 로딩 / 에러 / 비활성(disabled) 가 실제로 있는가?
  • 로딩 피드백이 즉각적인가 (100ms 이내 첫 피드백, 1s 이상이면 스켈레톤 또는 progress)?
  • 에러 메시지에 원인과 복구 동작이 같이 있는가?

D4. 인터랙션·모션

  • 전환 200ms 이하인가? 지나치게 느린 애니메이션 없는가?
  • 호버·포커스·활성 상태가 명확히 구분되는가?
  • prefers-reduced-motion 대응이 있는가? (스크린샷만으로 확인 어려우면 추정으로 표기)

D5. 접근성

  • 본문 대비 AA 4.5:1 이상인가? 시각적으로 애매하면 의심 플래그.
  • 키보드 포커스 링이 보이는가?
  • 터치 타깃 44×44px 이상인가?
  • 아이콘-only 버튼에 aria-label 있는가?

D6. 반응형·밀도

  • 모바일 뷰(360~430px)와 데스크톱(1280+)에서 모두 의미 있는 레이아웃인가?
  • 터치 영역 간격이 충분한가?
  • 표·리스트가 좁은 뷰에서 깨지지 않는가?

D7. 텍스트 품질

  • 버튼·라벨이 동사로 시작하고 동작을 명확히 기술하는가 ("OK"·"Submit" 남발 주의)?
  • 단위·맥락·변화량이 숫자와 함께 제시되는가?
  • 에러·경고 문구가 사용자 언어로 되어 있는가 (개발자 jargon 금지)?

D8. 신뢰·안전 표시

  • 비가역적 동작(삭제·결제·로그아웃)에 확인 단계가 있는가?
  • 파괴적 버튼의 시각 계급이 적절한가 (실수로 누르기 쉬운 위치 여부)?

Severity Rubric

  • BLOCK — 사용자가 과업을 완료하지 못하거나, 데이터·신뢰를 훼손하는 결함. 출시 전 해소 필수.
  • ASK — 사용자 의도·맥락에 따라 판단 갈리는 항목. 개발자·디자이너 확인 필요.
  • NOTE — 출시에 영향 없지만 다음 이터레이션에서 개선할 항목.

Output Format

## Frontend UX Review

### 요약
{3~5줄. 이 화면의 의도 · 핵심 리스크 · 전반 품질 소견}

### BLOCK (출시 전 해소 필요)
- [D2] 토큰 불일치: Button 높이가 36px/40px 혼용 — {파일:라인 또는 스크린샷 위치}
  - 근거: {확인 or 추정}
  - 제안: {구체적 수정안}

### ASK (사용자/디자이너 확인)
- [D4] 모달 진입 트랜지션 450ms — 의도된 무게감인가? 기본 200ms 로 낮추는 게 표준.

### NOTE (다음 이터레이션)
- [D7] 빈 상태 카피 "No data" → 사용자 언어로 교체 권장.

### 확인 범위
- 확인한 입력: {스크린샷 3장 / 코드 diff / ...}
- 미확인 항목: {모션 실제 속도 / 스크린리더 동작 / ...}

Read the full file on GitHub · 128 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 · 128 lines · 103 tokens per session scan A ecfce73173b2

Subscribe to this mod's changes

frontend-ux-reviewer is an agent published in the GitHub repository leee880619-commits/ClaudeCode-Harness-Setup-Assistant (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,812 once invoked, about $0.0005 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

prototype-builder

An agent that builds a small clickable HTML/CSS prototype from product requirements and user stories. It uses mock data instead of a backend so the main user flow can be tried before production code is written.

andrewcigan/vibe-dev-plugin · 52 tokens

ux-inclusive-evaluator

Inclusive design and WCAG 2.2 accessibility evaluator for the /user-experience skill. Performs WCAG 2.2 compliance audits across Perceivable, Operable, Understandable, and Robust principles (conformance levels A, AA, AAA) and applies Microsoft Inclusive Design methodology including Persona Spectrum analysis…

geekatron/jerry · 199 tokens

pn-frontend-developer

Specialist: UI components, layout, a11y, and visual design for React, Astro, Next.js, or vanilla HTML/CSS/JS. Invoke directly for focused frontend work or let pn-build route to it.

perniemann/pnCore · 51 tokens

speccrew-feature-designer

SpecCrew Feature Designer. Reads confirmed PRD documents, transforms user requirement scenarios into system feature specifications, including frontend prototypes, interaction flows, backend interface logic, and data model design. Does not focus on specific technology implementation details, but outlines how to…

charlesmu99/speccrew · 0 tokens

team-accessibility-reviewer

Stage 2 reviewer focused on WCAG 2.2 AA, semantic HTML, keyboard support, and screen reader UX.

hazarsozer/crucible-cc · 31 tokens

design-expert

Frontend design specialist creating distinctive, high-quality interfaces.

onmyway133/claude-code-plugins · 13 tokens