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/.agents/skills/hc-test/SKILL.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/skills/harness-base/harness-control/hc-test)<a href="https://agentmods.dev/skills/harness-base/harness-control/hc-test"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-test/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/skills/harness-base/harness-control/hc-test"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-test.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 | $0.00258 | $0.03679 |
| Opus 5.5 | $0.00103 | $0.01472 |
| Sonnet 5.5 | $0.00052 | $0.00736 |
| Haiku 4.5 | $0.00026 | $0.00368 |
Grade A, and why
hc-test 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编排式产出测试（hc-test）
本 skill = 测试总监总谱（薄）：主 agent 当总监，按 docs/harness/testing-flow.md（流程唯一真相源·总纲）调度专职 worker 产出测试；进哪条线先读对应分线文件（testing-flow-{e2e,api,script,contract-check,regression}.md 五分线，清单以 testing-flow.md 场景表为准）。同 hc-prd「默认编排 + 用户覆盖」、同 hc-dev「写 → 派 reviewer 挑刺 → 回改 loop」。依据 ADR-0014（脚本线 ADR-0024）。
本文不复制流程长叙述——各小节引用总纲 / 分线文件对应小节，改流程只动那里。
① 何时用 / 何时不用
- 用：把需求（AC / FP / US / PRD）或接口来源（接口契约 / 指定源）转成测试用例；管「用例对需求 / 接口覆盖全不全」；做 e2e 用例 / api 用例；把用例落成可执行测试脚本并在 sandbox 调通（写跑一体，ADR-0024）；开发完成后做接口契约对照（脚本取数 + agent 对比，ADR-0026）；跑统一回归（存量脚本池，ADR-0027）。各线实现状态见
testing-flow.md「场景 × 实现状态」。 - 不用：产出需求走
hc-prd；写 / 改实现走hc-dev（脚本跑出实现的 bug 也回hc-dev修，本 skill 不改业务代码）；纯控制面 / 文档改动。
② 总监怎么派活
见 testing-flow.md「总监怎么派活」：
- 默认（A）：按手上产物 + 到了哪一步自动选场景（有 PRD 先做 e2e 用例；有接口契约（或用户指定接口来源）才做 api 用例；开发彻底结束 + 有用例才写脚本）。
- 用户指令最高优先级：随时点名做哪段 / 跳过哪段，覆盖默认（沿用
hc-prd总监模式）。 - 每步解耦、可跳任意一步：可以没用例、没脚本……都行。
- 进哪条线，先读对应分线文件（约束主体在分线文件 + worker 上下文，本总谱不复制）。
③ 场景 × worker（实现状态以 testing-flow 为准）
权威「场景 × 实现状态」表在 testing-flow.md（唯一真相源）——本总谱只列场景→worker 映射、不复刻状态列（rule-0012：复刻状态会漂，已栽过）。哪些已实现 / 哪些占位、各自触发条件，全看那张表：
| 场景 | worker → reviewer |
|---|---|
| e2e 用例 | hc-e2e-qa → hc-e2e-reviewer |
| api 用例 | hc-api-qa → hc-api-reviewer |
| 接口契约对照 | 总监调度（脚本取数 + agent 对比，不新建 worker） |
| 测试脚本 | hc-script-impl → hc-script-reviewer |
| 统一回归 | 总监调度（跑+修复用 hc-script-impl） |
已实现 / 占位与触发条件见
testing-flow.md「场景 × 实现状态」表 + 各分线文件——占位加时填空、不重构 skill 形态。
④ 用例线编排（e2e / api）—— 写 → 审 → 回改
形态 = hc-dev 那套「写 → 派 reviewer 挑刺 → 回改 loop」；各线主体在分线文件（testing-flow-e2e.md / testing-flow-api.md）。e2e 与 api 同构，只是输入源不同，总监按此编排：
- 取输入：
- e2e：需求，按 AC > FP > US > PRD（缺则略过、用现有的，不卡）。
- api：接口来源硬门槛——①
api-contract.md（hc-tech-design产）＞ ② 用户指定源（proto / OpenAPI / 路由表 / 接口代码）＞ ③ 都无 → MUST STOP（无源不臆造接口，rule-0008）。与 e2e「缺则略」不同、有硬地板。明细见testing-flow-api.md。
- 派 worker 写用例：e2e 派
hc-e2e-qa（套templates/e2e-test-case.md、每交互点 ×{成功,失败,边界}）、api 派hc-api-qa（套templates/api-test-case.md、与接口来源一一对应：每接口一用例、每业务异常各一 case）；预期锚唯一真实信号（rule-0009）、covers:声明覆盖、只写不跑（rule-0014 管用例这种文档产物）。要求写在 worker 子 agent 上下文里，本总谱不复制、明细见对应分线文件。 - 派 reviewer 审用例：e2e 派
hc-e2e-reviewer、api 派hc-api-reviewer（api reviewer 多一条「无接口来源硬产用例 → blocker」门槛复核 + 回契约原文对账）；只评不改，出结构化清单。 - 回改 loop：多视角并行对抗——fan out 对应 reviewer 多实例、各盯一个视角（覆盖 / 源符合 / 质量…）→ 汇总去重 → 总监派 worker 回改 → 复审 → 到覆盖齐、清单清零（末轮换新视角防假收敛；编排 pattern =
docs/harness/adversarial-review.md，ADR-0022，唯一真相源、引用不复制）。 test-cases-audit机检兜底：结构层闸（e2e 覆盖矩阵完整性 / api 的 EP·EX ↔covers:双向闭合，带「无·理由」逃生口）跑通、make verify绿。见下「两层防线」。- 提醒用户：产物落
docs/test-cases/<id>/（登记不漂移）；明确告诉用户用例齐了、覆盖闸过了，用例没跑（脚本线才跑，见 ⑤）。
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 · 81 lines · 258 tokens per session scan A f33a076a0f17
hc-test is a skill published in the GitHub repository harness-base/harness-control (22 stars, last pushed 3mo ago), licensed MIT. It adds 258 tokens to every session and 3,679 once invoked, about $0.0010 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 skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.