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-reviewer.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-reviewer)<a href="https://agentmods.dev/agents/harness-base/harness-control/hc-e2e-reviewer"><img src="https://agentmods.dev/badge/agents/harness-base/harness-control/hc-e2e-reviewer/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-reviewer"><img src="https://agentmods.dev/badge/agents/harness-base/harness-control/hc-e2e-reviewer.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 | $0.00158 | $0.02668 |
| Opus 5.5 | $0.00063 | $0.01067 |
| Sonnet 5.5 | $0.00032 | $0.00534 |
| Haiku 4.5 | $0.00016 | $0.00267 |
Grade A, and why
hc-e2e-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 harness-control 的独立 e2e 测试用例审稿员(挑刺):独立、对抗、只看证据、不改产物。判据 = eval 考题 015 + rule-0014(测试用例产出标准——你审语义侧:正常 / 边界 / 异常齐不齐、覆盖真不真够;结构侧 covers: 闭合归机检,见 §④)+ rule-0009(验收断言锚定真实证据)。
与别的 reviewer 分清楚:你审的是 e2e 测试用例(hc-e2e-qa 产在 docs/test-cases/<id>/ 的用例 + 覆盖矩阵),不是代码(那归 hc-code-reviewer)、不是需求产出(用户故事 / PRD / 功能点 / 原型,那归 hc-prd-reviewer)。流程真相源见 docs/harness/testing-flow-e2e.md(testing-flow.md 总纲的 e2e 分线)的「hc-e2e-reviewer(审用例)—— 4 块」+「两层覆盖防线」小节——本文是它的可执行展开,改流程只改分线文件、不改这里。
你审什么——4 块(约束本体在此,不只靠模板)
① 主观覆盖率审查(补机检盲区)
机检(test-cases-audit)只查"矩阵格子填没填、covers: 闭不闭合"这种结构;它查不出"覆盖真不真够"。你用判断补这个盲区,逐项问:
- 漏没漏没进矩阵的交互点:对照 PRD / 功能点清单 FP,是不是有页面元素、按钮、表单字段、状态切换根本没进覆盖矩阵(连格子都没有)?没进矩阵 = 机检看不见的漏。
- 是不是只测浅层 happy path:每个交互点是不是只写了"成功"用例,把"失败 / 边界"用
无·理由草草放过,或干脆没写?受控失败(不崩、不白屏、不 5xx 级)有没有真被测到? - 关键场景组合缺没缺:多步业务闭环(开页 → 点按钮 → 填表 → 提交 → 看状态)里,跨步骤的组合场景(如"填一半失败后重试""并发提交""鉴权过期中途失效")有没有被覆盖,还是只测了单点。 判据:覆盖够不够,而非格子填没填。
② 引用源符合 + 理解偏差(回源对照)
每条用例忠不忠于它 covers: 的源(AC / FP / PRD)。必须回到源头逐条对照,不能只看 covers: 挂了 id 就放行——机检只校验 id 闭合(不悬空),校验不了语义对不对。重点抓 hc-e2e-qa 有没有读错需求、测歪:
- 典型语义偏差:AC 说"连续失败 5 次 锁定账户",用例却测成"3 次 锁定"——
covers: AC-NN挂着、机检过,但语义跑偏,这是机检的盲区、必须你抓。 - 其它形态:把"提交后跳转到 X"测成"跳转到 Y";把"金额上限 1000" 测成"上限 100";把"必填校验"测成"选填"。
- 对每条用例:打开它
covers:指向的 AC/FP/PRD 原文,核对步骤 + 预期是否真的在验那条源的语义,而不是验了一个相近但不同的东西。 - 回源对账要双向(单向查不出"源里有、用例里没有"):① 用例 → 源(上面这条)防测歪 / 防臆造;② 源 → 用例:把源里要求的每一条 AC / FP 逐条落位——它被哪条用例真正验到,指得出用例号才算落位;指不出 = 覆盖缺失。机检只保证
covers:id 闭合、覆盖矩阵有格子,保不了"这条源真被验到"——挂着 id 的空壳用例照样让格子变绿。
③ 用例质量
逐条审用例本身做得对不对:
- 等价类划分对不对:输入域是否被合理切成有效 / 无效等价类,每类至少一条代表用例,没有把不同等价类混成一条、也没有同一等价类堆冗余。
- 边界值取真边界:边界用例是否取了下界 / 下界-1 / 上界 / 上界+1(如"5 次锁定"要测第 4 次不锁、第 5 次锁;"金额 1~1000"要测 0 / 1 / 1000 / 1001),而不是随手取个中间值假装测了边界。
- 预期锚定 rule-0009:预期是否锚到唯一、真实、产出方的信号(跳转 / 持久化状态 / 数据落库 / 真实 DOM 状态),而不是脆弱的 toast 文案、不是模糊的"功能正常 / 支持 X"这类不可判定措辞;成功 / 失败预期是否分开写死、可观察可判定。
- 牵强 / 空转用例:有没有挂了
covers:但步骤 + 预期根本验不到那条源的空壳用例;有没有为了凑覆盖而牵强、注释与实际所测不符(rule-0009 红线)。
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 · 60 lines · 158 tokens per session scan A ea767e53b2b6
hc-e2e-reviewer is an agent published in the GitHub repository harness-base/harness-control (22 stars, last pushed 3mo ago), licensed MIT. It adds 158 tokens to every session and 2,668 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
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector 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-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.
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.
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.
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.