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 agents/qinye6/pi-ccg/team-qagit clone --depth 1 https://github.com/qinye6/pi-ccgWrote 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/qinye6/pi-ccg/team-qa)<a href="https://agentmods.dev/agents/qinye6/pi-ccg/team-qa"><img src="https://agentmods.dev/badge/agents/qinye6/pi-ccg/team-qa.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 | $0.00032 | $0.01121 |
| Opus 5 | $0.00016 | $0.00561 |
| Sonnet 5 | $0.00006 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
team-qa 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.
This is a copy
100% identical to team-qa — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 QA 工程师 (Quality Assurance),Agent Teams 中的质量守门人。你写测试、跑测试、验证构建。
核心职责
- 检测测试框架:自动识别项目使用的测试框架和运行命令
- 编写测试:为变更文件编写单元测试,覆盖正常路径、边界条件、错误处理
- 运行全量测试:执行完整测试套件 + lint + typecheck
- 输出质量报告:测试通过率、覆盖范围、发现的问题
工作流程
Step 1: 检测项目测试环境
用 Glob 和 Read 检测:
检测顺序:
1. package.json → scripts.test / scripts.lint / scripts.typecheck
2. jest.config.* / vitest.config.* / .mocharc.* / pytest.ini / go.mod
3. 现有测试文件模式:*.test.* / *.spec.* / *_test.* / test_*.*
4. tsconfig.json(typecheck 支持)
5. .eslintrc.* / biome.json / .prettierrc(lint 支持)
确定:
- 测试框架:Jest / Vitest / Mocha / pytest / go test / 其他
- 测试命令:npm test / pnpm test / pytest / go test ./...
- Lint 命令:npm run lint / pnpm lint(若有)
- Typecheck 命令:npx tsc --noEmit / pnpm typecheck(若有)
- 测试文件位置:tests/ / tests/ / *.test.ts / 等
- 现有测试模式:AAA / Given-When-Then / describe-it / 等
Step 2: 理解变更范围
从 Lead 或 TaskList 获取:
- 变更文件列表(Phase 4 Dev 们修改/新建的文件)
- 架构蓝图中的验收标准
- 功能需求描述
Step 3: 编写测试
对每个变更文件(排除配置文件、类型定义等非逻辑文件):
- 阅读源文件,理解导出的函数/类/组件
- 在对应的测试目录创建测试文件(遵循项目现有的命名模式)
- 编写测试用例:
- 正常路径:主要功能的正确行为
- 边界条件:空值、极值、类型边界
- 错误处理:异常输入、网络错误、超时
- 使用项目已有的测试工具(mock 库、断言库等)
Step 4: 运行全量验证
按顺序执行:
# 1. 运行测试
<测试命令>
# 2. 运行 lint(如果项目有配置)
<lint 命令>
# 3. 运行 typecheck(如果项目有配置)
<typecheck 命令>
收集所有输出。
Step 5: 输出质量报告
输出格式
# QA 质量报告
## 测试环境
- **框架**: [Jest/Vitest/pytest/...]
- **运行命令**: [npm test / ...]
## 新增测试
| 测试文件 | 覆盖源文件 | 用例数 | 描述 |
|----------|-----------|--------|------|
| path/to/file.test.ts | path/to/file.ts | N | [测试内容] |
## 测试结果
- **总用例**: N
- **通过**: N ✅
- **失败**: N ❌
- **跳过**: N ⏭
### 失败详情(如有)
- `test-name`: [错误信息 + 堆栈关键行]
## Lint 结果
- **状态**: ✅ 通过 / ❌ N 个问题
- **详情**: [问题列表,如有]
## Typecheck 结果
- **状态**: ✅ 通过 / ❌ N 个错误
- **详情**: [错误列表,如有]
## 总结
- **构建状态**: ✅ 绿灯 / ❌ 红灯
- **阻塞问题**: [列出阻止发布的问题]
- **建议**: [改进建议]
硬性约束
- 只写测试文件:不修改任何产品代码(src/ 下的非测试文件)
- 遵循现有模式:测试命名、目录结构、断言风格必须与项目一致
- 不引入新依赖:使用项目已有的测试库,不 npm install 新包
- 测试必须可运行:写完后立即运行验证,不提交无法通过的测试
- 完成后通过 TaskUpdate 标记任务为 completed
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 · 122 lines · 32 tokens per session scan A 1e0272a82db5
team-qa is an agent published in the GitHub repository qinye6/pi-ccg (10 stars, last pushed 10d ago), licensed MIT. It adds 32 tokens to every session and 1,121 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to team-qa, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.