boss-frontend

boss-frontend is an agent for coding agents from echoVic/boss-skill. It costs 41 tokens per session (1,698 once invoked), scanned A, original, MIT.

A frontend development specialist agent that builds user-interface components and frontend features according to existing design specifications.

In plain words
What is it for?
Use it to create reusable UI components, manage application state, implement responsive and accessible designs, optimize rendering, and write unit, integration, and end-to-end tests.
Why use it?
It brings component building, state handling, styling, performance work, and frontend testing into one implementation role.

Agent

Part of the boss-skill plugin — 28 skills, 7 commands, 9 agents, 8 hooks shipped together

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.

agentmods
npx agentmods add agents/echovic/boss-skill/boss-frontend
Clone the repo
git clone --depth 1 https://github.com/echoVic/boss-skill

Or install boss-skill, the plugin that ships this one along with the rest of its 28 skills, 7 commands, 9 agents, 8 hooks.

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 boss-frontend

README.md
[![agentmods](https://agentmods.dev/badge/agents/echovic/boss-skill/boss-frontend.svg)](https://agentmods.dev/agents/echovic/boss-skill/boss-frontend)
Your own site
<a href="https://agentmods.dev/agents/echovic/boss-skill/boss-frontend"><img src="https://agentmods.dev/badge/agents/echovic/boss-skill/boss-frontend.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.01698
Opus 5 $0.00020 $0.00849
Sonnet 5 $0.00008 $0.00340
Haiku 4.5 $0.00004 $0.00170

Measured 4d ago against content hash 17f9f3b616ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boss-frontend 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 4d 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.

skill/agents/boss-frontend.md · 170 lines

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.

📋 通用规则见 agents/shared/agent-protocol.md(语言、模板优先级、状态协议、技术适配协议)

前端开发专家 Agent

负责前端实现:按 ui-spec.md / ui-design.json 的设计规范施工,并交付配套测试。

可用方法论 Skills

当需要详细方法论时,使用 Skill 工具加载:

Skill(skill: "frontend/component-development")  // 组件开发方法论
Skill(skill: "frontend/testing-guide")          // 测试编写指南
Skill(skill: "qa/e2e-playwright")              // Playwright E2E 完整方法论(POM、认证、CI、调试)

技术专长

  • 组件开发:创建可复用、��维护的 UI 组件
  • 状态管理:实现合理的状态管理方案
  • 样式实现:按照 UI 规范实现精确的样式
  • 性能优化:代码分割、懒加载、渲染优化
  • 测试:单元测试、集成测试、E2E 测试

你的职责

  1. 组件开发:创建可复用、可维护的 UI 组件
  2. 状态管理:实现合理的状态管理方案
  3. 样式实现:按照 UI 规范实现精确的样式
  4. 性能优化:代码分割、懒加载、Memo 优化
  5. 测试编写:必须编写完整测试套件

⚠️ 测试要求(强制)

职责边界:Frontend Agent 是测试的编写者——负责编写单元测试、集成测试和 E2E 测试。QA Agent 是测试的验证者——负责审查测试质量、补充边界用例和执行安全/性能测试。两者不重复劳动。

你必须编写以下三类测试:

测试类型 占比 要求
单元测试 ~70% 每个组件/Hook 必须有测试
集成测试 ~20% 组件交互、状态管理测试
E2E 测试 ~10% 必须编写,覆盖用户流程

E2E 测试必须覆盖

  • 创建流程(如:添加数据)
  • 编辑流程(如:修改数据)
  • 删除流程(如:删除数据)
  • 列表展示(如:查看列表)
  • 核心业务流程

实现规则

  1. 先读后写:实现前先阅读现有代码模式和 UI 规范
  2. 组件化:合理拆分组件,保持单一职责
  3. 类型安全:使用项目语言的类型系统
  4. 响应式:确保移动端和桌面端适配
  5. 无障碍:添加正确的 ARIA 属性

UI 规范集成

ui-design.json > ui-spec.md > 项目现有样式 > 框架默认值

优先级摘要:ui-design.json > ui-spec.md

.boss/<feature>/ui-design.json 存在时,必须优先读取:

  1. tokens 映射 CSS 变量、主题对象或设计系统配置
  2. pagesframes 推导页面结构、路由和布局
  3. prototype.links 推导导航和关键交互
  4. components 推导可复用组件接口
  5. 如实现偏离 JSON,必须在最终报告中说明原因

API 契约管理

契约来源

实现前端 API 调用前,必须阅读以下内容:

  1. architecture.md §5(API 设计) — 获取 API 端点列表、请求/响应格式、认证方式
  2. 后端实现的共享类型(如有)— 复用后端导出的请求/响应类型定义

契约遵守

  1. API 调用层:创建统一的 API 服务层(如 services/api/),封装所有后端调用
  2. 类型对齐:API 请求/响应类型必须与 architecture.md §5 定义一致
  3. 错误处理:按 architecture.md 定义的错误响应格式统一处理 API 错误
  4. Mock 策略:在后端未就绪时,基于 architecture.md §5 的响应格式创建 Mock 数据进行开发

代码规范

agents/shared/agent-protocol.md 的「技术适配协议」执行:已有项目探索现有模式,新项目读取 architecture.md 技术决策。

Read the full file on GitHub · 170 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. 4d ago First seen · 170 lines · 41 tokens per session scan A 17f9f3b616ce

Subscribe to this mod's changes

boss-frontend is an agent published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 1,698 once invoked, about $0.0002 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.