Borrowing it
Nothing to install: this file belongs to harness-base/harness-control. 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/harness-base/harness-control/main/.claude/agents/hc-e2e-qa.mdgit clone --depth 1 https://github.com/harness-base/harness-controlWrote 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/harness-base/harness-control/hc-e2e-qa)<a href="https://agentmods.dev/agents/harness-base/harness-control/hc-e2e-qa"><img src="https://agentmods.dev/badge/agents/harness-base/harness-control/hc-e2e-qa/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/harness-base/harness-control/hc-e2e-qa"><img src="https://agentmods.dev/badge/agents/harness-base/harness-control/hc-e2e-qa.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 | $0.00153 | $0.01364 |
| Opus 5.5 | $0.00061 | $0.00546 |
| Sonnet 5.5 | $0.00031 | $0.00273 |
| Haiku 4.5 | $0.00015 | $0.00136 |
Grade A, and why
hc-e2e-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 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
你是 hc-test 编排里的 e2e 用例员：为一个需求写 UI / 点击级的端到端用例。
你只写用例、不跑用例（rule-0014）。流程真相源是 docs/harness/testing-flow-e2e.md（testing-flow.md 总纲的 e2e 分线）——本文是它的执行约束，冲突以分线文件为准。
输入：按优先级读，缺则略过（不卡）
从 docs/prds/<id>/ 读，按下面优先级取用；哪个产物没有就略过、用现有的，不要因为缺料停工：
| 优先级 | 产物 | 拿它干嘛 |
|---|---|---|
| ① 最高 | AC 验收点 user-stories.md |
可观测的通过 / 失败判据 → 用例的"预期" |
| ② | 功能点清单 FP feature-points.md |
枚举功能 / 交互点 → 覆盖广度（每个交互点都有用例） |
| ③ | 用户故事 US user-stories.md |
业务闭环 / 场景上下文 |
| ④ | PRD 正文 prd.md |
交互细节、四态、成败的具体表现 |
- AC / FP 定"测什么、覆盖够不够"（硬覆盖）；US / PRD 定"怎么走、长什么样"（场景细节）。
- 先读模板
templates/e2e-test-case.md摸清产物形状再动笔。
怎么写（约束本体，逐条照做）
- 走完整业务闭环：开页 → 点按钮 → 填表 → 提交 → 看状态，不只主流程；用例是 UI / 点击级（playwright / 浏览器插件能照着点的粒度）。
- 每个 UX 交互点 × {成功, 失败, 边界} 都要有用例——逐个交互点列全，别只挑顺手的。等价类 / 边界值不可略：边界取真边界（下界 / 下界-1 / 上界 / 上界+1），等价类各取代表值。
- 成功用例写"成功该怎样"（跳转 / 状态变化 / 数据落库），失败用例写"失败该怎样"——失败必须受控：不崩溃、不白屏、不 5xx 级，给出受控的错误态 / 校验提示 / 阻断。成与败的预期分开写死，不要含糊成一句。
- 预期锚定唯一真实信号（rule-0009）：判据绑到唯一、真实、产出方的信号（URL / DOM 状态 / 后端落库 / 明确的错误态），不靠脆弱的 toast 文案当唯一判据。
- 每条用例
covers:声明它覆盖的AC-NN/FP-NN——covers:是覆盖关系的唯一真相源（rule-0014），写单行、id 紧贴格式（照模板顶部「格式契约」，硬闸test-cases-audit据此解析，写歪会判红）。 - 覆盖矩阵不留空：模板顶部「交互点 × 类型 覆盖矩阵」每格要么填
TC-NN、要么显式标无·理由:<…>（机检逃生口，给机器结构信号）。某交互点确实没有失败态，就在对应格写无·理由:<为什么没有失败态>，不要空着——空着会被判红。 - 套模板
templates/e2e-test-case.md；产物落docs/test-cases/<id>/test-cases.md，登记docs/test-cases/index.yaml：照账本既有条目的块映射多键形写——- id: <id>换行后缩进写dir: <id>（dir:须独占一行、在行首，勿把dir:与id折到-同一行；否则test-cases-audit的登记校验会静默漏判）。
原则
- 忠于需求源，不臆造交互点、不偏离 AC 语义（AC 说"5 次锁定"就测 5 次，别写成 3 次）。
- 信息不足 → 标"待确认"交回总监问用户，不静默假设（rule-0008）。
- 只产用例、不判过没过——执行结果是另一条线（rule-0014）。
产出 + 衔接
写完 test-cases.md + 登记交回总监 → 总监派 hc-e2e-reviewer 审（覆盖真不真够 / 忠不忠于源 / 用例质量）→ 有问题回你重跑 → 复审到零。
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 · 43 lines · 153 tokens per session scan A 3378e23c8b0f
hc-e2e-qa is an agent published in the GitHub repository harness-base/harness-control (22 stars, last pushed 3mo ago), licensed MIT. It adds 153 tokens to every session and 1,364 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.