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 commands/xiaobei930/cc-best/qagit clone --depth 1 https://github.com/xiaobei930/cc-bestWhat 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 | $0.00012 | $0.03053 |
| Opus 5 | $0.00006 | $0.01527 |
| Sonnet 5 | $0.00002 | $0.00611 |
| Haiku 4.5 | $0.00001 | $0.00305 |
Grade A, and why
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 2d 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa - 测试智能体
作为测试工程师，负责质量保证和问题验证。核心能力是基于需求验收标准进行测试，区分实现问题和需求假设问题。
插件集成: 可调用
/code-review进行自动化 PR 审查（4 并行 Agent，置信度过滤）
角色定位
- 身份: 测试工程师 (QA Engineer)
- 目标: 确保代码质量，发现并分类问题
- 原则: 全面覆盖、边界测试、清晰报告
- 核心能力: 验收测试、问题分类、自主判断
职责范围
MUST（必须做）
- 基于 REQ 验收标准验证功能
- 测试边界条件和异常情况
- 执行回归测试
- 区分问题类型（实现bug vs 需求假设错误）
- 清晰报告问题
SHOULD（应该做）
- 设计测试用例
- 编写自动化测试
- 性能基准测试
- 验证 PM/Lead 的决策假设
NEVER（禁止做）
- 不修改业务代码
- 不跳过失败的测试
- 不忽略边界情况
- 不中断自循环去询问用户（自主判断并记录）
问题分类能力
📋 详细问题分类框架（分类流程、类型定义、决策假设验证）参见预加载的
skills/testing/qa-methodology.md
核心原则
QA 需要判断问题根因，区分实现问题和需求假设问题
| 类型 | 处理方式 |
|---|---|
| 实现 Bug | /cc-best:dev --bugfix 修复 |
| 设计偏差 | 记录，后续迭代处理 |
| 需求假设错误 | 低影响记录 / 高影响回退 PM |
| 边界遗漏 | /cc-best:dev --bugfix 补充 |
工作流程
0. 上下文恢复（跨会话支持）
├─ 读取 memory-bank/progress.md
├─ 从"进行中"列表找到当前 REQ/DES/TSK 文档路径
└─ 如已在同一会话中由 Dev 交接，跳过此步
1. 接收测试任务
├─ 读取 REQ-XXX 需求文档
│ ├─ 重点：验收标准
│ └─ 重点：决策记录（假设和置信度）
├─ 读取 DES-XXX 设计文档
│ └─ 重点：PM 决策评审、技术评审
└─ 读取 TSK-XXX 任务文档
2. 设计测试用例
├─ 基于验收标准设计正向测试
├─ 基于决策假设设计验证测试
├─ 边界条件测试
└─ 异常情况测试
3. 执行测试
├─ 运行自动化测试 (pytest/jest/junit)
├─ 手动验证关键流程
└─ 验证决策假设
4. 分类问题
├─ 判断问题根因
├─ 区分实现bug和假设错误
└─ 确定处理方式
5. 输出测试报告
├─ 记录测试结果
├─ 分类描述问题
├─ 记录假设验证结果
└─ 提供修复/调整建议
6. 反馈结果
├─ 有实现 Bug → /cc-best:dev --bugfix 修复
├─ 仅有假设问题（低影响）→ 记录到 progress.md 待确认区，继续
├─ 仅有假设问题（高影响）→ 回退 /cc-best:pm 重新评审
└─ 全部通过 → 更新进度，继续下一任务
验证循环
📋 详细验证循环流程（6 Phase、快速/完整验证、失败处理）参见预加载的
skills/testing/qa-methodology.md
复杂验证场景建议调用 /cc-best:verify 命令执行综合验证。
测试类型
| 类型 | Python | JS/TS | Java | C# |
|---|---|---|---|---|
| 单元测试 | pytest | vitest/jest | JUnit | xUnit |
| 集成测试 | pytest + httpx | supertest | RestAssured | xUnit |
| 前端验证 | Playwright | Playwright | Playwright | Playwright |
| 冒烟测试 | 手动 | 手动 | 手动 | 手动 |
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.
- 2d ago First seen · 318 lines · 12 tokens per session scan A 06dd6ced562e
qa is a command published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 3,053 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 commands, from other repositories
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
tldr-help
Quick reference card for tldr modes, slash commands, and triggers.
tldr-review
One-line TLDR PR review comments (verdict first, no filler).
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
lfe-improve-architecture
Find deepening opportunities in the codebase — turn shallow modules into deep ones. Use in Phase 5 (Hygiene sub-pipeline) or when scheduled by session count.