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.
npx skills add leee880619-commits/ClaudeCode-Harness-Setup-Assistant --skill frontend-designgit clone --depth 1 https://github.com/leee880619-commits/ClaudeCode-Harness-Setup-AssistantWrote 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.
[](https://agentmods.dev/skills/leee880619-commits/claudecode-harness-setup-assistant/frontend-design)<a href="https://agentmods.dev/skills/leee880619-commits/claudecode-harness-setup-assistant/frontend-design"><img src="https://agentmods.dev/badge/skills/leee880619-commits/claudecode-harness-setup-assistant/frontend-design/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.
<a href="https://agentmods.dev/skills/leee880619-commits/claudecode-harness-setup-assistant/frontend-design"><img src="https://agentmods.dev/badge/skills/leee880619-commits/claudecode-harness-setup-assistant/frontend-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00097 | $0.02323 |
| Opus 5 | $0.00048 | $0.01162 |
| Sonnet 5 | $0.00019 | $0.00465 |
| Haiku 4.5 | $0.00010 | $0.00232 |
Grade A, and why
frontend-design 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
프론트엔드 UI를 사람이 의도적으로 다듬은 수준으로 설계·구현·리뷰한다. "AI 디폴트"(뻔한 카드 나열, 평균적 간격, 기본 shadow)를 거부하고 의도·토큰·상태·접근성을 모두 통제한다.
작업 절차
- Intent — 대상 사용자 · 핵심 과업 · 톤을 1~2줄로 명시. 참조 사례 3개를 머릿속으로 비교.
- Tokens — 색·타이포·스페이싱·라운드·그림자·모션 토큰. reference/semantic 2계층 분리.
- Components — 프리미티브 단위로 해부. 상태 매트릭스(default/hover/focus-visible/active/disabled/loading/empty/error).
- Compose — 페이지·뷰를 컴포넌트 조합으로. 반응형 breakpoint 명시.
- Micro-interaction — 전환 150~250ms,
ease-out/spring.prefers-reduced-motion대응. - A11y pass — WCAG AA 4.5:1 (가능하면 APCA Lc ≥ 60), 키보드 포커스, ARIA, 터치 타깃 44×44.
- Review —
frontend-ux-reviewer에이전트가 있으면 감사 요청.
핵심 원칙 (압축 요약)
- AI 디폴트 거부: 모든 선택에 "왜" 를 답할 수 없으면 바꾼다.
- Raw 리터럴 금지: 컴포넌트 코드에 hex·rgb·임의 px 값 직접 금지. semantic 토큰만.
- 타입 스케일 1.125 or 1.25: 랜덤 크기 금지. 본문 16px+, 줄 길이 45~75자, line-height 1.5±0.1.
- 4/8px grid: 모든 간격은 그리드 값. "눈대중" 금지.
- 상태 커버리지: 프리미티브마다 최소 6개 상태 + 빈/에러/스켈레톤.
- 아이콘 한 세트: Lucide / Phosphor / Radix / Heroicons 중 하나만.
- 피드백 즉각성: 100ms 이내 첫 반응, 1s 이상 작업은 스켈레톤/progress.
- 파괴적 동작 방어: 삭제·결제·로그아웃은 확인 단계 + 계급 낮은 위치.
색상 원칙 (내장 · 외부 의존 없음)
이 스킬은 다음 색상 규칙을 자체 내장한다. 추가 스킬 설치 없이 이 섹션만으로 팔레트·대비·토큰 설계가 가능하다.
토큰 2계층 (필수)
- Reference tokens: 원시 색 — 팔레트 정의·변환·진단에만 사용.
- 예:
ref.brand.500 = oklch(0.62 0.18 254)
- 예:
- Semantic tokens: 역할에 매핑 — 컴포넌트는 오직 semantic 만 참조.
- 예:
semantic.surface.default = ref.neutral.50,semantic.text.muted = ref.neutral.600,semantic.state.danger = ref.red.600
- 예:
- 컴포넌트 파일에 raw hex/rgb 리터럴 금지. 테마·다크 모드 전환이 불가능해진다.
색 공간 선택
- OKLCH 우선: 명도(L) 조작이 균일 — hover/active 상태를
oklch(from var(--ref) calc(l - 0.08) c h)로 유도 가능. - HSL 피하기: 같은 명도(L) 값이라도 hue 에 따라 실제 밝기 차이가 커 무작위 결과 생성.
- hex: 최종 출력·디자인 토큰 export 에만.
대비 기준
- WCAG AA: 본문 4.5:1, 큰 텍스트(18.66px 이상 또는 14pt bold) 3:1, UI 컴포넌트/그래픽 객체 3:1. 최소 기준.
- APCA (권장): Lc ≥ 60 (본문), Lc ≥ 45 (큰 텍스트), Lc ≥ 30 (비필수 UI). 지각적으로 더 정확.
- 다크 모드에서 흰 배경용 색을 그대로 쓰지 말 것. 명도 축을 뒤집은 별도 semantic 매핑.
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 · 123 lines · 97 tokens per session scan A 99f282f55f2f
frontend-design is a skill published in the GitHub repository leee880619-commits/ClaudeCode-Harness-Setup-Assistant (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,323 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.
Other skills, from other repositories
speccrew-knowledge-techs-ui-analyze
Analyze existing frontend UI codebase to extract and summarize page styles, layout patterns, component usage, and design conventions. Generates comprehensive UI style guides for each platform (PC, Mobile, etc.) including page type classifications, component libraries, layout patterns, and styling conventions. Used to…
speccrew-knowledge-techs-generate-ui-style
Generate UI style analysis documents for a specific frontend platform using XML workflow blocks. Analyzes page types, components, layouts, and styling conventions from source code. Only applicable to frontend platforms (web, mobile, desktop).
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
ui-design-executor
Use this as UIDesigner's default execution skill. It contains the baseline design, accessibility, HTML, runtime-safety, responsive, taste, and verification rules needed by ordinary UI work. Do not load the separate system, control, taste, color, renderer, or craft skills merely to repeat these baseline rules.
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live Figma runtime.
ui-design-system
Use this skill when creating, extending, or auditing a product UI system. It adapts Better Design-style design-system discipline without requiring an external runtime package.