What is design-review?

A visual review command for finished HTML, CSS, SVG, images, documents, and interface screenshots. It checks for design patterns that can make an output look generic or obviously machine-made.

Use it on a file, screenshot, or local development URL after creating a visual deliverable. It scores the result across typography, color, layout, and other checklist categories, then reports suggested corrections.

It catches visual issues after production, such as overused fonts, gradients, rounded corners, shadows, or emojis, before the work is shown to others. It is separate from a code review, which checks logic and implementation.

design-review — Command for Claude Code by Ramsbaby

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/Ramsbaby/jarvis

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ramsbaby/jarvis/design-review/github.svg)](https://agentmods.dev/commands/ramsbaby/jarvis/design-review)

Your own site

<a href="https://agentmods.dev/commands/ramsbaby/jarvis/design-review"><img src="https://agentmods.dev/badge/commands/ramsbaby/jarvis/design-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ramsbaby/jarvis/design-review"><img src="https://agentmods.dev/badge/commands/ramsbaby/jarvis/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 128 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,237 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.

Model	Per session	Once invoked
Fable 5.1	$0.00128	$0.02237
Opus 5	$0.00064	$0.01118
Sonnet 5	$0.00026	$0.00447
Haiku 4.5	$0.00013	$0.00224

Measured 10d ago against content hash 096f58353cc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

design-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.

dotfiles/claude/commands/design-review.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-review — AI Slop 감식관

한 줄: 만든 뒤 눈으로 봤을 때 "AI가 만들었네" 라는 인상을 주는 진부한 요소를 생산 후 자동 감식.

/review와의 경계 (혼동 금지)

스킬	대상	방법
`/review`	코드 로직·버그·스타일	Dev+Reviewer 에이전트
`/design-review`	시각 산출물 (HTML·CSS·SVG·이미지)	체크리스트 기반 감식
`discord-visualization.md` (룰)	생산 전 금지 가이드	정적 룰

보완 관계: discord-visualization.md는 "만들 때 쓰지 마"는 룰, /design-review는 "다 만든 뒤 남았는지 검사"하는 감식관. 충돌 아닌 이중 방어.

언제 사용합니까

/my-resume 생성 직후
/blog-writer 초안 완료 후
자비스맵(jarvis-board) 컴포넌트 추가 후
HTML 리포트 / 슬라이드 / 디스코드 카드 / SVG 다이어그램 작성 직후
주인님이 "AI 티 나?", "디자인 어때?" 하시는 순간

입력

세 가지 중 하나:

파일 경로 — .html, .svg, .css, .md(마크다운 프레이밍 포함), .tsx/.jsx(Styled Component·Tailwind)
스크린샷 — .png, .jpg, .webp (이미지 Read 후 시각 분석)
URL — localhost:3000류 개발 서버 → chrome MCP로 렌더 캡처 후 분석 (MCP 가용 시)

감식 체크리스트 (5 카테고리 × 4 항목 = 20점)

A. 서체 (Typography) — 4점

[A1] Inter / Roboto / Arial 등 진부한 산세리프 기본값 사용 감지
[A2] 헤딩·본문 모두 동일 서체만 사용 (대비 없음)
[A3] font-family 명시 없이 브라우저 기본값 의존
[A4] 한국어 콘텐츠인데 영문 전용 서체만 스펙

B. 색상 (Color) — 4점

[B1] 흰 배경 + 보라 그라데이션 조합 (AI 슬롭 1호)
[B2] 푸른색 그라데이션 대시보드 헤더
[B3] 악센트 색상이 #FF0000, #00FF00 같은 원색
[B4] 다크 모드 배경이 순흑 #000000 (대비 과잉)

C. 레이아웃 (Layout) — 4점

[C1] 좌우 50:50 카드 반복 (3섹션 이상 동일 패턴)
[C2] 12-column grid 무비판 사용 (콘텐츠 구조 무관)
[C3] 모든 컨테이너 max-width: 1200px 중앙 정렬 동일
[C4] 헤더·사이드바·푸터 3분할 템플릿 그대로

D. 컴포넌트 (Component) — 4점

[D1] 둥근 모서리 8px + 박스 그림자 + 호버 lift 3종 세트 남발
[D2] 버튼 모두 동일 스타일 (primary/secondary 구분 없음)
[D3] 아이콘이 모두 outline heroicons 기본
[D4] 카드 패딩·간격 모두 16px·24px 정박

E. 콘텐츠 (Content) — 4점

[E1] 이모지 남발 (한 섹션 3개 이상) — 단, 주인님 CLAUDE.md는 CLI 출력 이모지 허용 (맥락 판단)
[E2] "혁신적", "놀라운", "차세대" 같은 공허한 수식어
[E3] 플레이스홀더 텍스트(Lorem ipsum, Sample text)가 프로덕션에 남음
[E4] 숫자 다 0 또는 100으로 하드코딩된 차트 (실데이터 미반영)

실행 프로토콜

Phase 1 — 입력 식별 + 카테고리 확정

# 파일 경로 입력 시
file "$INPUT"  # 타입 확인

Read the full file on GitHub · 155 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.

10d ago First seen · 155 lines · 128 tokens per session scan A 096f58353cc6

Subscribe to this mod's changes

design-review is a command published in the GitHub repository Ramsbaby/jarvis (17 stars, last pushed 18d ago), licensed MIT. It adds 128 tokens to every session and 2,237 once invoked, about $0.0006 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 2026-08-30.

Claude Code Code review Design and UX ai-agent automation claude discord-bot lancedb

critique

Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.

educlopez/ui-craft · 56 tokens

design-review