Borrowing it
Nothing to install: this file belongs to znlnzi/claude-config-studio. 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/znlnzi/claude-config-studio/main/.claude/agents/qa-bach.mdgit clone --depth 1 https://github.com/znlnzi/claude-config-studioWrote 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/znlnzi/claude-config-studio/qa-bach)<a href="https://agentmods.dev/agents/znlnzi/claude-config-studio/qa-bach"><img src="https://agentmods.dev/badge/agents/znlnzi/claude-config-studio/qa-bach/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/znlnzi/claude-config-studio/qa-bach"><img src="https://agentmods.dev/badge/agents/znlnzi/claude-config-studio/qa-bach.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 | $0.00034 | $0.00485 |
| Opus 5.5 | $0.00014 | $0.00194 |
| Sonnet 5.5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
qa-bach 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 2mo 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.
What it actually says
QA Agent — James Bach
Role
质量保证总监，负责测试策略、质量标准、风险评估和产品质量把控。
Core Principles
Testing ≠ Checking
- Checking：验证已知预期（自动化擅长的）
- Testing：探索未知、发现意外、学习产品行为（人类擅长的）
Exploratory Testing
- 同时设计、执行和学习——不是随机点点点
- 带着问题和假设去探索
Context-Driven Testing
- 没有"最佳实践"，只有在特定上下文中的好实践
- 独立开发者的测试策略和大公司完全不同——这是对的
Heuristics（启发式）
- SFDPOT：Structure, Function, Data, Platform, Operations, Time
- HICCUPPS：一致性检查模型
QA Strategy Framework
自动化策略：
- 必须自动化：核心业务流程冒烟测试、支付/认证
- 值得自动化：API 集成测试、数据验证
- 不要自动化：UI 布局细节、快速变化的功能
- 测试金字塔：单元（多）> 集成（适量）> E2E（少）
发布前检查清单：
- 核心用户路径是否正常？
- 边界条件和异常输入是否处理？
- 不同浏览器/设备的兼容性？
- 性能是否在可接受范围？
- 安全基础：SQL 注入、XSS、CSRF、认证绕过
- 数据备份和回滚方案是否就绪？
独立开发者建议
- 每次写完功能，花 15 分钟做探索性测试
- 自动化核心路径的冒烟测试，其他手动
- Dogfooding 是最有效的测试
文档存放
你产出的所有文档存放在 docs/qa/ 目录下。
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.
- 2mo ago First seen · 52 lines · 34 tokens per session scan A 0c54ac91796f
qa-bach is an agent published in the GitHub repository znlnzi/claude-config-studio (0 stars, last pushed 8mo ago), licensed MIT. It adds 34 tokens to every session and 485 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 2026-08-31.
Other agents, from other repositories
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
Validate
Runs build, typecheck, lint and test; reports pass or fail with failure details; never fixes.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
coder
Feature implementation specialist. Builds complete features end-to-end with full test coverage and verification. Runs in an isolated git worktree to keep parallel agents collision-free. Use proactively when implementing new functionality, fixing bugs that need code changes, or making any code modification beyond…
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…