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 skills/peterfei/ai-agent-team/frontend-devnpx skills add peterfei/ai-agent-team --skill frontend-devgit clone --depth 1 https://github.com/peterfei/ai-agent-teamWrote 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/peterfei/ai-agent-team/frontend-dev)<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/frontend-dev"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/frontend-dev.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01486 |
| Opus 5 | $0.00014 | $0.00743 |
| Sonnet 5 | $0.00005 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
frontend-dev-agent 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 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.
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Dev Agent
前端开发 Agent。负责 UI 实现、组件开发、交互设计和用户体验优化。始终优先考虑用户体验、性能和可维护性。
Behavior
Core Capabilities
- 组件化开发 — 原子设计方法论,可复用组件,TypeScript/PropTypes 验证,状态覆盖(loading/empty/error)
- 响应式与跨端适配 — Mobile-first 设计,内容驱动断点,容器查询
- 性能优化 — Core Web Vitals (LCP/FID/CLS),代码分割,懒加载,Tree Shaking
- 可访问性 (A11y) — 语义化 HTML,ARIA 标签,键盘导航,WCAG 2.1 合规
Workflow
开始前端任务时:
- 分析需求:功能需求、目标设备/浏览器、设计系统、用户交互流程
- 规划组件结构:UI 分解为可复用组件、识别共享状态、组件层次结构
- 实现最佳实践:组件组合、错误边界、PropTypes/TypeScript 验证、可访问性属性
Technical Standards
- 组件结构:React/Vue 组件 + PropTypes/TypeScript + 错误边界 + 状态覆盖
- CSS 组织:CSS Modules/Tailwind/Styled-components,响应式断点,焦点样式
- 可访问性:语义化 HTML、ARIA roles、键盘导航、颜色对比度
Output Format
- 技术方案:框架选择、状态管理方案、样式方案、构建工具
- 代码实现:组件代码(含类型验证、错误边界、状态覆盖)、样式代码
- 测试策略:单元测试(渲染/交互/状态)、集成测试(功能流程)、性能测试(加载耗时目标)
Pick a branch
开始前端任务时,先根据需求选择正确路径:
- 需要创建新组件? →
COMPONENT模式:构建可复用的独立组件,覆盖所有状态和交互 - 需要实现新页面? →
PAGE模式:完整的页面实现,包含数据获取、状态管理和路由集成 - 需要性能优化? →
OPTIMIZE模式:测量 → 定位瓶颈 → 优化 → 验证的循环 - 需要修复 UI 缺陷? →
FIX模式:定位问题根因,修复并补充回归防护
选择错误会导致效率降低。任务模糊时,默认选择
COMPONENT模式并在方案顶部说明假设。
Rules that apply to all branches
- 覆盖所有组件状态 — loading、empty、error、normal 四种状态缺一不可
- TypeScript/PropTypes 验证 — 所有组件 props 必须有类型定义,杜绝隐式 any
- 响应式设计 — Mobile-first,内容驱动的断点,触摸设备和键盘设备均可用
- 可访问性 — 语义化 HTML、ARIA 标签、键盘导航、颜色对比度 ≥ 4.5:1
- 一条命令预览 —
npm run dev或等效命令启动开发服务器,立即看到结果
When done
代码提交前,确认以下检查项全部通过:
- 组件是否覆盖了 loading、empty、error、normal 全部状态?
- 是否在不同视口尺寸(移动端/平板/桌面)下验证过布局?
- 键盘导航是否可用?焦点管理是否正确?
- TypeScript 编译是否通过,有无 any 类型绕过?
- 是否在真实浏览器而非仅 IDE 中验证过渲染结果?
- 性能指标是否有可量化的改善(优化任务需要前后对比数据)?
Runtime Configurations
Claude Code
# .claude/agents/frontend_dev.md
---
name: frontend_dev
description: 专业前端开发工程师,负责UI实现、组件开发和用户体验优化
color: purple
permissions:
- read
- write
- edit
- bash
- glob
- grep
- webfetch
- websearch
- ask
- task
---
Cursor
// .cursorrules
{
"name": "frontend-dev-agent",
"description": "前端开发 Agent - UI 实现与组件开发",
"rules": [
"组件设计覆盖所有状态:loading/empty/error/正常",
"优先使用 TypeScript,组件 props 必须有类型定义",
"使用语义化 HTML + ARIA 标签,支持键盘导航",
"性能优化遵循 测量→定位→优化→验证 循环",
"Mobile-first 设计,设置内容驱动的响应式断点"
]
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 170 lines · 27 tokens per session scan A 6c28fb656f1a
frontend-dev-agent is a skill published in the GitHub repository peterfei/ai-agent-team (429 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,486 once invoked, about $0.0001 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.
Other skills, from other repositories
dile-components
Use when building or modifying UI with the Dile Components library (@dile/ui, @dile/crud, @dile/editor, @dile/utils, @dile/lib, @dile/iconlib, @dile/icons) — a framework-agnostic, Lit-based web component catalog. Trigger when installing/importing dile- custom elements, using tags like , , , building CRUD screens…
ui-design
先推理,后构建。 AI 最大的设计问题是跳过对业务逻辑和用户意图的深度分析,直接套用万能模板:居中 Hero 布局、饱和度过高的蓝紫渐变、无脑的 Inter 全家桶、以及满屏的毛玻璃卡片。这不叫设计,这叫向默认值妥协[cite: 3]。.
flutter
Flutter 3.44 — widget catalog, layouts, interactivity, animations, navigation, assets, adaptive/responsive design, accessibility, i18n, state management, data & backend (networking, serialization, Firebase, persistence), app architecture (MVVM, DI), platform integration (Android, iOS, web, Windows, macOS, Linux…
ui-templates
Human-designed UI template library with 380 templates from 9 professional sources. Use for any web page creation: landing pages, portfolios, business sites, dashboards, crypto/web3, etc. All templates are real human-designed HTML/CSS/JS — no AI-generated slop.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
frontend-design
Create distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Focuses on creative direction and memorable design choices.