vibe-e2e

vibe-e2e is a skill for Claude Code from xushuodasd/VIBE-Claude-Plugin. It costs 72 tokens per session (3,934 once invoked), scanned B, original, MIT.

A browser-based end-to-end check of a running project. It tests pages, buttons, forms, browser output, and API responses as a real user would.

In plain words
What is it for?
Use it to start the project, open it in a browser, visit each route, test interactions, check console errors and APIs, and produce a report with screenshots and blocking issues.
Why use it?
It catches problems that code-level tests can miss, such as blank pages, broken controls, styling failures, and missing API responses before delivery.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vibe-claude-plugin plugin — 25 skills, 1 command shipped together

Good fit Use it to start the project, open it in a browser, visit each route, test interactions, check console errors and APIs, and produce a report with screenshots and blocking issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xushuodasd/vibe-claude-plugin/vibe-e2e
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.

Any agent
npx skills add xushuodasd/VIBE-Claude-Plugin --skill vibe-e2e
Clone the repo
git clone --depth 1 https://github.com/xushuodasd/VIBE-Claude-Plugin

Made for: Claude Code.

Or install vibe-claude-plugin, the plugin that ships this one along with the rest of its 25 skills, 1 command.

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 vibe-e2e

README.md
[![agentmods](https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-e2e/github.svg)](https://agentmods.dev/skills/xushuodasd/vibe-claude-plugin/vibe-e2e)
Your own site
<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.

agentmods 80×15 button for vibe-e2e

Your own site · 80×15
<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>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00072 $0.03934
Opus 5 $0.00036 $0.01967
Sonnet 5 $0.00014 $0.00787
Haiku 4.5 $0.00007 $0.00393

Measured 10d ago against content hash 944d5bdbb113, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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
skills/vibe-e2e/SKILL.md · 380 lines

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

  1. npm install -D playwright (旧包名)
  2. pip install playwright && python -m playwright install chromium (Python 版)
  3. 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

Read the full file on GitHub · 380 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. 10d ago First seen · 380 lines · 72 tokens per session scan B 944d5bdbb113

Subscribe to this mod's changes

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.