What is webqa-agent CLAUDE.md?

Team instructions for a Python web-testing project. They organize shared rules for code quality, testing, Git, and browser testing, and require research before complex work or unfamiliar dependencies.

Use them when changing the web-testing codebase, especially when adding libraries, designing asynchronous code, configuring tools such as Docker or CI/CD, or implementing security features.

They reduce errors caused by outdated library knowledge, unclear project rules, or inconsistent coding and testing practices.

webqa-agent CLAUDE.md — Instructions file for coding agents by MigoXLab: Team instructions for a Python web-testing project.

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 instructions/migoxlab/webqa-agent/claude-md

Clone the repo

git clone --depth 1 https://github.com/MigoXLab/webqa-agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/migoxlab/webqa-agent/claude-md.svg)](https://agentmods.dev/instructions/migoxlab/webqa-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/migoxlab/webqa-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/migoxlab/webqa-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,877 This file is loaded in full into every session.

When invoked 4,877 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.04877	$0.04877
Opus 5	$0.02439	$0.02439
Sonnet 5	$0.00975	$0.00975
Haiku 4.5	$0.00488	$0.00488

Measured 4d ago against content hash 6052f5c3b365, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

webqa-agent CLAUDE.md 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.

CLAUDE.md · 546 lines

How it starts

The opening of the file, as written. The whole thing — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

团队共享的 webqa-agent 项目指南。

重要提示:本文件是团队共享的,所有开发者都应遵循这些规范。个人偏好和本地配置应放在 CLAUDE.local.md(不会被 git 跟踪)。

模块化规则引用

本项目遵循模块化规则组织:

Python 代码质量: .claude/rules/python-quality.md
测试模式: .claude/rules/testing.md
Git 工作流: .claude/rules/git-workflow.md
浏览器测试: .claude/rules/domain-specific/browser-testing.md

这些规则继承自全局配置(~/.claude/CLAUDE.md 和 ~/.claude/rules/),并增加了 webqa-agent 特定的要求。

研究和规划 (CRITICAL)

对于复杂任务或涉及第三方依赖,必须先做调研:

1. 使用 Context7 MCP 工具

工具:mcp__plugin_context7_context7__resolve-library-id 和 query-docs
获取最新的库文档和最佳实践
了解正确的 API 使用方式
避免基于过时知识的幻觉

2. 使用联网搜索

工具:WebSearch
查找最新的技术文章和实践
了解常见问题和解决方案
验证技术决策的合理性

3. 调研场景示例

✅ 集成新的第三方库(Playwright, LangChain, FastAPI 等)
✅ 实现复杂的异步模式或并发控制
✅ 使用不熟悉的 Python 特性或设计模式
✅ 配置复杂的工具链(Docker, CI/CD 等)
✅ 实现安全相关功能(认证、加密等)

4. 调研步骤

a. 识别任务中的三方依赖或复杂技术点
b. 使用 Context7 获取官方文档
c. 使用 WebSearch 查找最佳实践和常见陷阱
d. 基于调研结果制定实现计划
e. 开始编码实现

❌ 不要做的事情:

不要想当然地认为知道某个库的用法
不要跳过调研直接开始规划和写代码
不要基于旧版本的知识进行实现

代码质量要求 (CRITICAL)

规范性和可读性

类型注解:严格模式 - 所有函数必须有类型注解
注释密度:中等 - 复杂逻辑需要注释,简单逻辑不需要
错误处理:显式 - 明确的 try-except 和错误处理
日志级别:生产环境 info,调试时 debug

避免代码冗余

❌ 不要创建功能重复的类、方法或变量
❌ 不要复制粘贴代码,使用函数/方法复用
❌ 不要保留已废弃的代码(直接删除,Git 有历史记录)
✅ 重构时整合相似功能
✅ 使用继承和组合减少重复

命名规范

类名:PascalCase
函数/方法:snake_case
常量:UPPER_SNAKE_CASE
私有成员:_leading_underscore
避免模糊命名:temp, tmp, data 等

详细规范见:.claude/rules/python-quality.md

兼容性和稳定性 (CRITICAL)

避免非必要的 breaking changes 和破坏性修改:

1. 保持架构和使用的一致性

❌ 不要随意修改公共 API 的签名
❌ 不要改变已有功能的行为方式
❌ 不要删除正在使用的代码而不考虑影响
✅ 新功能应该向后兼容
✅ 废弃功能使用 deprecation 警告而不是直接删除
✅ API 变更需要提供迁移指南

2. 新特性设计原则

零学习成本优先:新功能应该符合现有模式
可选而非强制:新特性默认关闭或可选启用
渐进式增强:不强迫用户立即升级或改动
文档完善:新功能需要清晰的使用文档

Read the full file on GitHub · 546 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.

4d ago First seen · 546 lines · 4,877 tokens per session scan A 6052f5c3b365

Subscribe to this mod's changes

webqa-agent CLAUDE.md is an instructions file published in the GitHub repository MigoXLab/webqa-agent (228 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,877 tokens to every session, about $0.0244 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.

Browser automation E2E testing LLM Testing agent qa qa-agent vibe-coding web-development

webqa-agent CLAUDE.md