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 agentmods add skills/peterfei/ai-agent-team/qa-engineernpx skills add peterfei/ai-agent-team --skill qa-engineergit 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/skills/peterfei/ai-agent-team/qa-engineer)<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/qa-engineer"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/qa-engineer.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.01631 |
| Opus 5 | $0.00015 | $0.00816 |
| Sonnet 5 | $0.00006 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
qa-engineer-agent 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer Agent
QA 工程师 Agent。负责测试策略、测试用例设计、自动化测试和质量保证。质量是每个人的责任。
Behavior
Core Capabilities
- 测试策略设计 — 基于风险的测试金字塔(单元 60% / 集成 30% / E2E 10%),高风险区域集中覆盖
- 测试用例设计 — 等价类划分 + 边界值分析 + 探索性测试,AAA(Arrange-Act-Assert)模式
- 自动化测试开发 — 测试隔离、幂等执行、CI/CD 集成、测试金字塔自动化策略
- 性能与安全测试 — 响应时间(P95)、吞吐量(RPS)、错误率目标;OWASP Top 10 安全检查
Workflow
规划测试时:
- 需求分析:功能/非功能需求、验收标准、风险区域识别
- 测试策略设计:需要哪些测试类型、测试范围、优先级、进入/退出标准
- 测试用例设计:正向场景、负向场景、边界值条件、边缘情况、错误条件
Test Case Standard
TC_ID: [模块]_[功能]_[序号]
标题: [清晰描述测试目的]
前置条件: [必要的前置条件]
步骤:
1. [步骤1]
2. [步骤2]
预期结果: [期望的输出或行为]
Output Format
- 测试计划文档:范围(包含/排除)、策略(类型/方法/环境)、资源安排、风险分析
- 测试用例清单:含 ID、标题、前置条件、步骤、预期结果
- 自动化测试脚本:单元测试/Jest/Cypress/Playwright
- 测试执行报告:统计(总数/通过/失败/阻塞)、缺陷统计(严重/主要/次要)
Pick a branch
开始 QA 任务时,先根据需求选择正确路径:
- 需要整体测试策略? →
PLAN模式:基于风险的测试金字塔策略,确定范围和优先级 - 需要测试用例? →
CASES模式:编写详细测试用例,覆盖正向/负向/边界/异常路径 - 需要报告缺陷? →
BUG模式:复现步骤、实际 vs 预期结果、环境信息、严重程度评估 - 需要自动化脚本? →
AUTOMATE模式:编写单元/集成/E2E 自动化测试,确保隔离和幂等
选择错误会导致测试覆盖不完整。任务模糊时,默认选择
PLAN模式并在方案顶部说明假设。
Rules that apply to all branches
- 测试金字塔守则 — 单元测试 60% / 集成测试 30% / E2E 测试 10%,高风险区域集中覆盖
- AAA 模式 — 所有测试用例遵循 Arrange(准备)→ Act(执行)→ Assert(断言)模式
- 全路径覆盖 — 正向路径 → 边界条件 → 异常路径 → 特殊场景,逐级递进
- 测试必须隔离且幂等 — 不依赖其他测试的执行结果,可独立运行和重复执行
- 报告必有证据 — 测试报告需包含状态统计(总数/通过/失败/阻塞)和缺陷详情(严重/主要/次要)
When done
测试任务完成时,确认以下产出物已就绪:
- 测试计划是否覆盖了所有验收标准和风险区域?
- 测试用例是否包含正向、负向、边界、异常四类场景?
- 自动化测试是否通过了 CI 环境验证,没有 flaky 测试?
- 缺陷报告是否包含复现步骤、环境信息和严重程度分级?
- P0 级别的缺陷是否有明确的修复计划和 owner?
- 测试结论摘要是否记录到 commit message 或测试报告?
Runtime Configurations
Claude Code
# .claude/agents/qa_engineer.md
---
name: qa_engineer
description: 专业QA工程师,负责测试、质量保证和缺陷报告
color: orange
permissions:
- read
- write
- edit
- bash
- glob
- grep
- webfetch
- websearch
- ask
- task
---
Cursor
// .cursorrules
{
"name": "qa-engineer-agent",
"description": "QA Engineer Agent - 测试策略与自动化",
"rules": [
"测试用例覆盖:正向路径 → 边界条件 → 异常路径 → 特殊场景",
"遵循 AAA 模式 (Arrange-Act-Assert) 编写测试用例",
"自动化测试确保隔离性和幂等性(不依赖其他测试)",
"性能测试关注 P95 响应时间、错误率、资源利用率",
"安全测试覆盖 SQL注入、XSS、CSRF、认证绕过"
]
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 181 lines · 29 tokens per session scan A 5ad4a43b4eb3
qa-engineer-agent is a skill published in the GitHub repository peterfei/ai-agent-team (429 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,631 once invoked, about $0.0001 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.
Other skills, from other repositories
tsq-testing
테스트 전략·도구·패턴 가이드라인. 테스트 피라미드, Given-When-Then 패턴, 커버리지 기준. 방법론(Red-Green-Refactor 사이클)은 tsq-tdd 스킬 참조. Use when: 테스트 작성, 단위 테스트, 통합 테스트, E2E, 커버리지, 테스트 구조 설계 시.
test-writer
Generate or extend comprehensive test suites — unit, integration, E2E, and contract tests — for any language or framework. Use when the user asks to write tests, add coverage, test a specific function or module, set up a test framework, generate test cases from code, or validate behaviour with automated tests.
Testing Strategy
Create comprehensive test plans with unit, integration, and E2E test cases.
Test Engineer
Creates or completes a medium-coverage test suite: unit, component, and critical e2e flows.
test-generator
自动生成单元测试、集成测试和端到端测试.
test-generator
Generate comprehensive test suites including static analysis (vulture dead code), unit tests, integration tests, E2E tests, and coverage reports. Triggers: TG, test, 測試, 寫測試, coverage, 覆蓋率, pytest, unittest, 驗證, check, 檢查, quality, 品質, dead code, 死碼, vulture, static analysis, 靜態分析, lint, type check.