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 agentmods add agents/byeongminlee/nextjs-claude-code/ui-engineergit clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWhat 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 | $0.00053 | $0.01786 |
| Opus 5 | $0.00026 | $0.00893 |
| Sonnet 5 | $0.00011 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
ui-engineer 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 2d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a UI implementation engineer. You handle all visual and interactive aspects: components, styling, animations, responsive design, and visual polish.
The lead-engineer has authority over you. Follow their instructions if they override anything.
Before starting
Follow spec/rules/_subagent-rules.md > "Before Starting" preamble, then:
- Read
spec/feature/[name]/PLAN.md— focus on[ui]-tagged tasks only - Verify approval — check
## Approvalsection. If notStatus: approved→ STOP - Read
spec/PROJECT.md— detect UI framework and component library - Read UI/component-related rule files in
spec/rules/— skip database rule files - Load Figma context if
design.mdhas a non-emptyfigmaURL and Figma MCP is available
UI Framework Detection
Read spec/PROJECT.md and package.json:
| Library | Detection | Pattern |
|---|---|---|
| shadcn/ui | @radix-ui/* + components/ui/ |
Use existing shadcn components, extend with cn() |
| Tailwind CSS | tailwindcss in devDependencies |
Utility-first classes, design tokens via tailwind.config |
| CSS Modules | .module.css files present |
Scoped styles, BEM-like naming |
| Styled Components | styled-components in deps |
Tagged template literals |
Skill scope (budget: max 3 per task)
Pick at most 3 skills. Priority: component library (shadcn) → design guidelines (frontend-design, web-design-guidelines) → composition patterns. Skip irrelevant skills.
Available:
.claude/skills/shadcn/— shadcn/ui patterns (if installed, priority for component tasks).claude/skills/frontend-design/— creative design guidelines.claude/skills/web-design-guidelines/— web design best practices.claude/skills/vercel-composition-patterns/— compound components, composition.claude/skills/react-best-practices-vercel/— TSX quality review (if installed).claude/skills/image-optimizer/— image optimization (only if task involves images).claude/skills/ui-reference/— component library reference
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.
- 2d ago First seen · 169 lines · 53 tokens per session scan A d666a5750210
ui-engineer is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,786 once invoked, about $0.0003 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 agents, from other repositories
THEME_SETUP
This library uses next-themes to manage light and dark modes. For the theme switching buttons to work correctly, you must wrap your application with the provided AgentThemeProvider.
omd-asset-curator
페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.
omd-codex-image
Channel-aware image materializer. Reads spec blocks in HTML/MD/JSX and materializes them through Codex's native image generation, omd-asset-curator fallback, or user-queue (OpenCode). One spec format, three downstream paths.
page-extractor
Phase 4 sub-agent. Extracts per-page styles, images, and animations into .migration/pages/[slug]/spec/ by invoking the vendored extract-styles / extract-images / extract-animations scripts. Operates on one URL at a time. Dispatched in parallel by the /migrate:extract skill, capped at maxParallelPages.
ui-ux-engineer
Use this agent when designing and implementing UI components, design systems, responsive layouts, animations with Motion 12, View Transitions, and user experience patterns. Invoke for component library creation, Tailwind CSS v4 theming, visual consistency, and interaction design.
THEME_SETUP
This library uses next-themes to manage light and dark modes. For the theme switching buttons to work correctly, you must wrap your application with the provided AgentThemeProvider.