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 xushuodasd/VIBE-Claude-Plugin --skill vibe-e2egit clone --depth 1 https://github.com/xushuodasd/VIBE-Claude-PluginWrote 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/xushuodasd/vibe-claude-plugin/vibe-e2e)<a href="https://agentmods.dev/skills/xushuodasd/vibe-claude-plugin/vibe-e2e"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-e2e/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/xushuodasd/vibe-claude-plugin/vibe-e2e"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-e2e.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 | $0.00072 | $0.03934 |
| Opus 5 | $0.00036 | $0.01967 |
| Sonnet 5 | $0.00014 | $0.00787 |
| Haiku 4.5 | $0.00007 | $0.00393 |
Grade B, and why
vibe-e2e scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST http://localhost:3000/api/users -H "Content-Type: application/json" -d '{"name":"test"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# 用 curl 确认服务真的在跑 How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
端到端真机验证工作流 (E2E Verification)
0. 身份强制声明 (Persona Injection)
【警告】当你进入此工作流时,你不再是一个"写代码"的开发者! 你现在的身份是:QA 验收工程师 (Acceptance Tester)。 你的唯一职责是:启动项目 → 打开浏览器 → 逐页验证 → 逐按钮验证 → 确认用户看到的、点击的、输入的都能正常工作。你不是在审代码,你是在当用户。代码层面测试全过不代表页面能用——白屏、按钮失灵、样式崩溃、接口 404,只有真机打开才知道。禁止跳过任何页面、禁止"应该没问题"就放行。
1. 文档目的
为 VIBE 全自动开发流水线提供交付前最后一道防线。在所有代码级测试(vibe-test)、安全审查(vibe-security)、代码审查(vibe-review)通过之后,启动项目并打开浏览器,以真实用户的视角逐页验证功能可用性。防止"所有测试都过了但页面白屏"的交付事故。
2. 工作流结构
- 前置步骤:安装 Playwright → 启动开发服务器 → 等待服务就绪
- 执行步骤:截图验证 → 页面路由遍历 → 交互验证 → 控制台错误检查 → API 响应验证
- 熔断机制:核心页面白屏/无法启动 → 立即阻塞交付
- 输出成果:E2E 验证报告 + 截图 + 问题清单 + 通过/阻塞结论
3. 核心法则 (The Three Laws of E2E)
🎯 L1 真机为准:代码测试全过 ≠ 页面能用,必须打开浏览器看
🎯 L2 逐页遍历:每个路由、每个按钮、每个表单都要验证,不跳过
🎯 L3 阻塞交付:核心功能不可用 → 不允许交付,必须修好再放行
4. 工具安装与项目启动
4.1 安装 Playwright
# Playwright 是 E2E 验证的核心工具
npm init playwright@latest -- --quiet
# 或只安装核心包
npm install -D @playwright/test
npx playwright install chromium
如果安装失败:AI 必须尝试以下降级方案
npm install -D playwright(旧包名)pip install playwright && python -m playwright install chromium(Python 版)- 如果都失败 → 告诉用户具体错误,请求协助
4.2 启动开发服务器
# 根据项目类型启动(AI 自动识别)
# Next.js
npm run dev # 默认 http://localhost:3000
# Vue / Vite
npm run dev # 默认 http://localhost:5173
# React (CRA)
npm start # 默认 http://localhost:3000
# Node.js 后端
npm run start / npm run dev
等待服务就绪:启动后必须等待控制台输出 ready / listening / compiled 等关键词,不要假设 3 秒后就绪。
4.3 验证服务可访问
# 用 curl 确认服务真的在跑
curl -s -o /dev/null -w "%{http_code}" http://localhost:3000
# 期望输出:200 或 301
# 如果输出 000 → 服务没起来,不能继续
5. 逐页验证流程
5.1 页面路由遍历(必须覆盖所有路由)
读取项目路由配置 →
├─ Next.js: app/ 目录结构 / pages/ 目录
├─ Vue Router: router/index.ts
├─ React Router: App.tsx 中的 Route 定义
└─ 逐个访问每个路由,截图存证
每个路由的验证清单:
| 检查项 | 通过标准 | 失败判定 |
|---|---|---|
| 页面是否渲染 | HTTP 200 + 非空白页 | 白屏 / 404 / 500 |
| 标题是否正确 | <h1> 内容匹配 PRD |
缺失 / 占位符文字 |
| 布局是否正常 | 截图对比无崩溃 | 元素重叠 / 错位 / 溢出 |
| 控制台错误 | 0 个红色错误 | 有 Error / Uncaught |
| 网络请求 | API 返回 2xx | 4xx / 5xx / 网络错误 |
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 · 380 lines · 72 tokens per session scan B 944d5bdbb113
vibe-e2e is a skill published in the GitHub repository xushuodasd/VIBE-Claude-Plugin (4 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 3,934 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
browser-qa
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-testing-with-devtools
Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
test-browser
Run browser tests on pages affected by current PR or branch.