Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/seekers2001/docs-governance/test-collaborationnpx skills add Seekers2001/docs-governance --skill test-collaborationgit clone --depth 1 https://github.com/Seekers2001/docs-governanceWrote 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/seekers2001/docs-governance/test-collaboration)<a href="https://agentmods.dev/skills/seekers2001/docs-governance/test-collaboration"><img src="https://agentmods.dev/badge/skills/seekers2001/docs-governance/test-collaboration.svg" alt="Measured on agentmods" 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 | $0.00183 | $0.02470 |
| Opus 5 | $0.00092 | $0.01235 |
| Sonnet 5 | $0.00037 | $0.00494 |
| Haiku 4.5 | $0.00018 | $0.00247 |
Grade A, and why
test-collaboration 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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测试协作治理（test-collaboration）
目标
用项目根目录的 TESTS.md 管理两类信息：
- 现有测试资产地图：项目已经有哪些测试、从哪里运行、保护什么。
- 必要测试点清单：哪些需求、规则、风险和 Bug 必须被测试保护，当前证据是否足够。
清单管理的是“为什么测、测什么、证据在哪”，测试代码仍然是可执行事实。不要把 TESTS.md 写成每个测试函数的镜像。
职责边界
| 资产 | 唯一职责 |
|---|---|
TESTS.md |
测试资产、必要测试点、缺口、状态和证据 |
| 测试代码 | 可执行输入、断言、fixture/fake 和边界模拟 |
REGRESSION.md |
模块下游、回归命令和改动后的重跑规则；只引用 TEST-ID |
| Spec/Issue | 成功标准、问题现象、影响、优先级、任务状态和排期的唯一来源 |
PROJECT_LOG.md |
只追加测试状态变化和交付结论，不复制整个清单 |
v1 由当前会话直接执行本 skill，不新增专用 agent、slash command 或强制脚本。
开始前读取
按存在性读取，不要求项目拥有全部文件：
TESTS.md与templates/TESTS.example.md。- 项目规则和地图，如
CLAUDE.md、AGENTS.md、CLAUDE_MAP.md。 - 测试目录、测试配置、CI 配置、标准测试入口和专用测试任务。
- Spec、Bug、Issue、审计、事故或回归清单；成功标准只引用，不复制进
TESTS.md。 REGRESSION.md，用于对齐模块回归命令与 TEST-ID。- 跨端接口的机器可读契约及生成/校验入口，例如 OpenAPI、JSON Schema、GraphQL schema 或 protobuf。
先识别仓库已有的测试框架和命名习惯，不强迫项目改成统一目录结构。
工作模式
1. 盘点现有测试资产
首次采用时做一次全量盘点，之后按事件增量维护：
- 找到标准测试入口，例如
pytest、npm test、make test或项目脚本。 - 扫描测试目录、配置和 CI；可以使用 collect/list 模式，但不要为了盘点执行高风险外部操作。
- 按模块、测试套件或关键流程聚合，禁止手抄每个测试函数。
- 标注层级、用途、执行组、外部依赖、位置和当前判断。
- 将资产判断为：必要、疑似重复、缺失或疑似废弃。盘点阶段只报告，不擅自删除或重写测试。
重新盘点由事件触发，不按日历机械执行：
- 首次建立
TESTS.md：全量扫描。 - 测试目录、测试配置、CI 或标准入口变化：重扫受影响区域。
- 新增或更新 TEST-ID、Bug：增量核对相关模块。
- 重大功能、接口、业务规则或安全边界变化：重扫对应链路。
- 交付前或
/governance-sync收尾：核对本次变更涉及的条目。 - 只有测试体系整体重构或地图明显失真时，才再次全量扫描。
2. 把需求、规则和风险转成 TEST-ID
每个必要测试点使用稳定 ID，例如 TEST-ORDER-001。至少记录：
- 状态：
待补、开发中、已覆盖、不适用。 - 来源：需求、规则、风险、Bug 或事故编号。
- 模拟输入与业务预期。
- 层级与用途。
- 执行组和真实/模拟边界。
- 测试文件、测试节点和可执行命令。
来源必须链接回 Spec/Issue 中的原始成功标准。TESTS.md 只回答“哪条证据验证它”，不得另写一份可独立漂移的业务标准。成功标准含糊时，回到需求澄清能力或请项目负责人确认，不由测试 Skill 猜测。
受控层级：单元、集成、契约、E2E、冒烟。
受控用途：规则保护、关键链路、回归保护、专项保护。需要多个用途时用逗号分隔，不能临时发明新值。
不适用 必须写理由，例如风险由 schema、类型系统或 lint 更合适地机械拦截。不能用“不好测”作为理由。
3. 把 Bug 转成回归保护
修复 Bug 时，必须二选一：
- 新增或关联一个 TEST-ID；或
- 明确记录为什么只能人工验收，以及人工验收步骤和证据。
TEST-ID 应复现真实失败形状，而不是换成更容易通过的相似输入。记录修复前失败、修复后通过的证据；如果无法先运行旧代码，至少说明复现依据和未实测项。
没有 TEST-ID 或明确的人工出口，不得宣称 Bug 已完整闭环。
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.
- 3d ago First seen · 147 lines · 183 tokens per session scan A 476d2152e8a6
test-collaboration is a skill published in the GitHub repository Seekers2001/docs-governance (11 stars, last pushed 21d ago), licensed MIT. It adds 183 tokens to every session and 2,470 once invoked, about $0.0009 per session on Opus 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 skills, from other repositories
testing-patterns
Testing patterns and principles. Unit, integration, mocking strategies.
js-in-html-testing
Test JS logic embedded in HTML using two-layer strategy - Python unit tests + Playwright browser integration tests.
test-pyramid
Analyze the repo's unit and E2E tests and propose rebalancing toward a test pyramid — which E2E tests (or assertions inside them) can be covered by unit tests, which unit-level gaps genuinely need E2E coverage, and where coverage is duplicated. Use when the user asks about test pyramid, test rebalancing, "should this…
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
check-and-test
Run lint checks (ruff for Python, Biome for TS/JS), type checks (pyright for Python, tsc for TS/JS), and the standard pytest tiers (unit + e2e + tests skipped during pre-commit). Investigates failures to determine if they are application bugs or test issues, and fixes application bugs rather than weakening tests. Does…
qa/test-strategy
测试策略和测试金字塔原则，定义单元测试、集成测试、E2E测试的分布和覆盖要求.