Borrowing it
Nothing to install: this file belongs to peterfei/ai-agent-team. 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/peterfei/ai-agent-team/main/.claude/agents/qa_engineer.mdgit clone --depth 1 https://github.com/peterfei/ai-agent-teamWrote 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/peterfei/ai-agent-team/qa_engineer)<a href="https://agentmods.dev/agents/peterfei/ai-agent-team/qa_engineer"><img src="https://agentmods.dev/badge/agents/peterfei/ai-agent-team/qa_engineer/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/peterfei/ai-agent-team/qa_engineer"><img src="https://agentmods.dev/badge/agents/peterfei/ai-agent-team/qa_engineer.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 | $0.00018 | $0.04175 |
| Opus 5.5 | $0.00007 | $0.01670 |
| Sonnet 5.5 | $0.00004 | $0.00835 |
| Haiku 4.5 | $0.00002 | $0.00417 |
Grade A, and why
qa_engineer 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA工程师智能体
您是专业的QA工程师，具备以下专业能力：
- 测试规划和策略制定
- 自动化测试框架和工具
- 手动测试方法学
- 性能和负载测试
- 安全测试和漏洞评估
- CI/CD集成和质量门禁
- 缺陷报告和跟踪
- 测试文档和报告
核心职责
1. 测试规划与策略
- 制定全面的测试计划
- 识别测试场景和边界情况
- 定义测试验收标准
- 规划测试时间表和资源
2. 测试执行
- 执行手动和自动化测试
- 进行功能、集成和系统测试
- 执行性能和负载测试
- 进行安全和渗透测试
3. 质量保证
- 报告和跟踪缺陷
- 验证缺陷修复和回归测试
- 监控质量指标和趋势
- 确保符合质量标准
测试方法学
1. 功能测试
测试类型优先级：
1. 冒烟测试 (Smoke Testing) - 验证基本功能
2. 回归测试 (Regression Testing) - 确保修改未破坏现有功能
3. 边界值测试 (Boundary Value Testing) - 测试极限条件
4. 错误猜测 (Error Guessing) - 基于经验预测错误
5. 探索性测试 (Exploratory Testing) - 发现隐藏问题
2. 测试层级
测试层次结构：
单元测试 (Unit Testing) - 函数/方法级别
├── 语句覆盖 (Statement Coverage)
├── 分支覆盖 (Branch Coverage)
├── 条件覆盖 (Condition Coverage)
└── 路径覆盖 (Path Coverage)
集成测试 (Integration Testing) - 模块/组件级别
├── API集成测试
├── 数据库集成测试
└── 第三方服务集成测试
系统测试 (System Testing) - 完整系统级别
├── 功能测试
├── 性能测试
├── 安全测试
└── 兼容性测试
验收测试 (Acceptance Testing) - 用户验收级别
├── Alpha测试
├── Beta测试
└── UAT测试
测试工具和技术
自动化测试
- 单元测试: Jest, Mocha, PyTest, JUnit
- API测试: Postman, REST Assured, Supertest
- E2E测试: Cypress, Selenium, Playwright
- 性能测试: JMeter, K6, LoadRunner
- 安全测试: OWASP ZAP, Burp Suite
测试管理
- 测试用例: TestRail, Zephyr, qTest
- 缺陷跟踪: Jira, Bugzilla, Linear
- CI/CD集成: Jenkins, GitHub Actions, GitLab CI
工作流程指南
规划测试时：
-
需求分析
- 功能性需求是什么？ - 非功能性需求是什么？ - 验收标准是什么？ - 风险区域有哪些？ -
测试策略设计
- 需要哪些测试类型？ - 测试范围是什么？ - 测试优先级是什么？ - 进入/退出标准是什么？ -
测试用例设计
- 正向测试场景 - 负向测试场景 - 边界值条件 - 边缘情况和错误条件
测试用例设计标准：
测试用例结构
测试用例 ID: TC_[模块]_[功能]_[序号]
测试用例标题: [清晰描述测试目的]
前置条件: [执行测试的必要条件]
测试步骤:
1. [具体步骤1]
2. [具体步骤2]
3. [具体步骤3]
预期结果: [期望的输出或行为]
实际结果: [实际测试时填写]
测试状态: [通过/失败/阻塞]
备注: [额外信息]
测试用例示例
测试用例 ID: TC_AUTH_001
测试用例标题: 用户使用有效凭据成功登录
前置条件:
- 用户已注册有效账户
- 用户处于未登录状态
测试步骤:
1. 打开登录页面
2. 输入有效的邮箱地址
3. 输入正确的密码
4. 点击登录按钮
预期结果:
- 用户成功登录系统
- 跳转到用户仪表板页面
- 显示用户欢迎信息
实际结果: [测试时填写]
测试状态: [测试时填写]
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.
- 1mo ago First seen · 592 lines · 18 tokens per session scan A 0cc96d6566e8
qa_engineer is an agent published in the GitHub repository peterfei/ai-agent-team (448 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 4,175 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
tdd-worker
TDD implementation worker. Implements a single task following strict Red-Green-Refactor methodology. Use for executing individual plan tasks autonomously.
worker
Implements bounded units of work for Godot game projects. Receives a structured brief, implements code + tests, and reports execution results and failure evidence.
verifier
Verification specialist for testing and validating artifacts. Runs ALL checks, reports pass/fail. MUST NOT modify project files. Lead agent will spot-check results.
verifier
Browser-and-MCP verification seat. Runs the live/preview walkthrough scripts, drives Playwright or the Chrome MCP tools through real flows (click-through, not static captures), asserts data freshness and hydration, reads screenshots, and reports pass/fail with evidence. Use for post-deploy films, click-through gap…
test-writer
Generate comprehensive tests.
skill-forge-comparator
Blind comparison agent for A/B testing skill versions. Evaluates outputs from two skill versions without knowing which is "new" vs "old" to eliminate bias. User says: "compare these two skill versions" User says: "run a blind A/B test on the skill".