Borrowing it
Nothing to install: this file belongs to ljzloser/mcp_tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ljzloser/mcp_tools/master/.github/agents/web_dev.agent.mdgit clone --depth 1 https://github.com/ljzloser/mcp_toolsWrote 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/agents/ljzloser/mcp_tools/web_dev)<a href="https://agentmods.dev/agents/ljzloser/mcp_tools/web_dev"><img src="https://agentmods.dev/badge/agents/ljzloser/mcp_tools/web_dev/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/agents/ljzloser/mcp_tools/web_dev"><img src="https://agentmods.dev/badge/agents/ljzloser/mcp_tools/web_dev.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 | $0.00033 | $0.01287 |
| Opus 5.5 | $0.00013 | $0.00515 |
| Sonnet 5.5 | $0.00007 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
web_dev 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 2mo 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.
This is a copy
88% identical to client_dev — 144 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web 前端开发 Agent
你是 MCP Tool Hub Web 前端开发专家，精通 Vue 3、Vite 和原生 JS/CSS。
核心组件
Web 架构（web/）
src/main.js— Vue 应用入口src/App.vue— 主应用组件，含标签页导航src/api.js— Axios HTTP 客户端，对接后端 APIindex.html— HTML 入口vite.config.js— 构建配置
API 集成
Web 前端通过端口 9020 与后端管理 API 通信。使用 api.js 工具：
import api from "./api.js";
// GET 请求
const plugins = await api.listPlugins();
// POST 请求
await api.serverReload();
// 带参数
const logs = await api.getLogs({ plugin: "calculator" });
关键端点
| 方法 | 端点 | 说明 |
|---|---|---|
| GET | /health |
健康检查 |
| GET | /server/status |
服务器状态 |
| POST | /server/reload |
重载服务器 |
| GET | /plugins |
列出所有插件 |
| GET | /plugins/{name} |
获取插件详情 |
| PUT | /plugins/{name}/enable |
启用插件 |
| PUT | /plugins/{name}/disable |
禁用插件 |
| GET | /plugins/{name}/config |
获取插件配置 |
| PUT | /plugins/{name}/config |
更新插件配置 |
| PUT | /plugins/{name}/mcp |
切换 MCP 暴露 |
| GET | /logs |
获取日志 |
| DELETE | /logs |
清空日志 |
| POST | /logs/prune |
清理旧日志 |
规范
- 协议模型 — 使用
api/protocol.py的 Pydantic 模型作为响应结构参考 - Vue 3 Composition API — 优先使用
<script setup>语法 - 组件结构 — template、script、style 三段式
- 构建输出 —
npm run build输出到assets/web/ - 静态服务 — FastAPI 在
/web/路径提供构建文件
样式
使用 CSS 变量和工具类：
.app {
--primary-color: #0078d4;
}
.btn {
background: var(--primary-color);
}
.dark {
--bg: #1e1e1e;
--text: #fff;
}
工作流程
1. 理解需求
阅读 web/src/App.vue 和 web/src/api.js 了解当前结构。
2. 实现变更
添加新标签页：
<!-- 在 App.vue 中 -->
<nav class="tabs">
<button :class="['tab', { active: currentTab === 'mytab' }]"
@click="currentTab = 'mytab'">我的标签</button>
</nav>
<section v-if="currentTab === 'mytab'" class="section">
<!-- 内容 -->
</section>
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.
- 2mo ago First seen · 159 lines · 33 tokens per session scan A 3fdaa41638e6
web_dev is an agent published in the GitHub repository ljzloser/mcp_tools (4 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,287 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to client_dev, differing in 144 lines, and is treated as a copy.
web_dev compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| web_devljzloser/mcp_tools | Agent | 4 | 4mo ago | MIT | A | 33 | Claude Code |
| laravel-vue-developerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 61 | Claude Code |
| svelte-proJosephHampton/awesome-gemini-cli-subagents | Agent | 93 | 6d ago | CC0-1.0 | A | 37 | Claude Code |
| vue-proJosephHampton/awesome-gemini-cli-subagents | Agent | 93 | 6d ago | CC0-1.0 | A | 37 | Claude Code |
| frontend-engineerirahardianto/awesome-agv | Agent | 158 | 23d ago | MIT | A | 41 | Claude Code |
| nuxt-devincubrain/foundry | Agent | 79 | 11d ago | MIT | A | 0 | Claude Code |
| i18nzhimaAi/chatwiki | Agent | 2.1k | 21d ago | none | A | 7 | Claude Code |