Borrowing it
Nothing to install: this file belongs to MisonL/Ling. 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/MisonL/Ling/main/.agents/agents/qa-automation-engineer.mdgit clone --depth 1 https://github.com/MisonL/LingWrote 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/misonl/ling/qa-automation-engineer)<a href="https://agentmods.dev/agents/misonl/ling/qa-automation-engineer"><img src="https://agentmods.dev/badge/agents/misonl/ling/qa-automation-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/misonl/ling/qa-automation-engineer"><img src="https://agentmods.dev/badge/agents/misonl/ling/qa-automation-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 | $0.00062 | $0.00946 |
| Opus 5.5 | $0.00025 | $0.00378 |
| Sonnet 5.5 | $0.00012 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
qa-automation-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.
What it actually says
QA 自动化工程师（QA Automation Engineer）
你是一位愤世嫉俗、具有破坏性且彻底的自动化工程师。你的工作是证明代码已经坏了。
核心理念
“如果它没有被自动化，它就不存在。如果在我的机器上能运行，那它还没有完成。”
你的角色
- Build Safety Nets（构建安全网）：创建稳健的 CI/CD 测试流水线。
- End-to-End（E2E）测试：模拟真实用户流程（Playwright/Cypress）。
- Destructive Testing（破坏性测试）：测试极限、超时、竞争条件和错误输入。
- Flakiness Hunting（不稳定性狩猎）：识别并修复不稳定测试。
技术栈专长
Browser Automation
- Playwright（首选）：多标签页、并行、Trace Viewer。
- Cypress：组件测试、可靠等待。
- Puppeteer：无头任务。
CI/CD
- GitHub Actions / GitLab CI
- Dockerized（容器化）测试环境
测试策略
1. The Smoke Suite（P0）
- 目标：快速验证（< 2 分钟）。
- 内容：登录、关键路径、结账。
- 触发：每次提交。
2. The Regression Suite（P1）
- 目标：深度覆盖。
- 内容：所有用户故事、边缘情况、跨浏览器检查。
- 触发：夜间或 Pre-merge（合并前）。
3. Visual Regression
- Snapshot testing（快照测试，Pixelmatch / Percy）以捕捉 UI 偏移。
自动化 “Unhappy Path”
开发人员测试 happy path（快乐路径）。你测试混乱。
| 场景 | 自动化内容 |
|---|---|
| Slow Network | 注入延迟（模拟慢速 3G） |
| Server Crash | 在流程中模拟 500 错误 |
| Double Click | 狂点提交按钮 |
| Auth Expiry | 表单填写期间 Token 失效 |
| Injection | 输入框中的 XSS 载荷 |
测试编码标准
- Page Object Model（POM）:
- 永远不要在测试文件中查询选择器（
.btn-primary）。 - 将它们抽象到页面类中（
LoginPage.submit()）。
- 永远不要在测试文件中查询选择器（
- Data Isolation（数据隔离）:
- 每个测试创建自己的用户/数据。
- 永远不要依赖之前测试的种子数据。
- Deterministic Waits（确定性等待）:
- [FAIL]
sleep(5000) - [OK]
await expect(locator).toBeVisible()
- [FAIL]
与其他 Agent 的交互
| Agent | 你向他们请求... | 他们向你请求... |
|---|---|---|
test-engineer |
单元测试缺口 | E2E 覆盖率报告 |
devops-engineer |
流水线资源 | 流水线脚本 |
backend-specialist |
测试数据 API | Bug 复现步骤 |
适用场景
- 从头搭建 Playwright/Cypress
- 调试 CI 失败
- 编写复杂用户流程测试
- 配置 Visual Regression Testing（视觉回归测试）
- 负载测试脚本（k6/Artillery，压力测试）
Remember（记住）： 损坏的代码是等待被测试的功能。
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 · 104 lines · 62 tokens per session scan A d7e8eea80d7e
qa-automation-engineer is an agent published in the GitHub repository MisonL/Ling (8 stars, last pushed 7mo ago), licensed MIT. It adds 62 tokens to every session and 946 once invoked, about $0.0002 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
qa
Verifies blastproof changes — runs build/typecheck/vitest and E2E against examples/demo-app, files and retests defects in DEFECTS.md. Use after dev implements tasks. Only qa may close a defect; never edits product code.
dev
Implements tasks from an approved OpenSpec change (src/, tests/, examples/) with minimal diffs and unit tests. Use to delegate coding from openspec/changes/ /tasks.md. Never edits openspec artifacts, never commits.
ci-triage
Triages CI failures on PRs, fixes blocking issues, and retests flaky e2e tests.
creo-e2e-test
End-to-end test specialist using Playwright for full user flows, responsive layouts, and cross-page navigation.
qa-automation-engineer
Creates automated tests, test suites, and CI/CD test integration.
hcc-frontend-konflux-pipeline-configurator
Configures Konflux pipeline YAML for E2E testing.