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 skills add hexagon-codes/hexclaw-desktop --skill devtestopsgit clone --depth 1 https://github.com/hexagon-codes/hexclaw-desktopWrote 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/hexagon-codes/hexclaw-desktop/devtestops)<a href="https://agentmods.dev/skills/hexagon-codes/hexclaw-desktop/devtestops"><img src="https://agentmods.dev/badge/skills/hexagon-codes/hexclaw-desktop/devtestops/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/hexagon-codes/hexclaw-desktop/devtestops"><img src="https://agentmods.dev/badge/skills/hexagon-codes/hexclaw-desktop/devtestops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.02483 |
| Opus 5.5 | $0.00020 | $0.00993 |
| Sonnet 5.5 | $0.00010 | $0.00497 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
devtestops 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 2d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevTestOps 全流程质量保障
授权与选择原则
用户要求、当前项目 AGENTS.md 和既有固定 CI 优先。阶段表、检查清单和关键词命中仅帮助定位问题，不自动授权新增用例、显示单测、真实调用、发布或安全专项。先复用有效证据，整体测试前说明局部验证为何不足；一个任务只执行能补齐实际缺口的方法，不默认逐层跑完。
在 HexClaw 生态不执行压力、负载、soak 或通用安全专项；UI 验证默认人工。新增单测先确认具体业务意图，真实模型、IM、未知恢复与前台操作沿各自授权。库的领域规则可直接验证公共 API，事务与锁使用真实依赖；应用验收核实际入口、终态、产物及副作用。
适用场景
当任务属于以下任一情况时，使用本 skill：
- 开始一个新需求/功能的开发，需要确定测试策略
- 代码开发完成，准备提测前的自检
- 需要判断当前变更需要哪些级别的测试
- 需要确认是否满足提测准入基线
- 上线前的最终检查清单
- 上线后的观察验收
不适用场景：
- 纯文档修改、注释调整等不涉及逻辑变更的场景
- 已有明确的测试方案且不需要重新评估时
核心原则
- 核心链路必须验证 — 主流程跑不通不能提测
- 验证对应真实风险 — 仅明确风险且已有证据不足时，选择授权内的定向方法，不按标签自动启动专项
- 提测准入有底线 — 基础项没过不进正式提测
- 上线不只看启动 — 要看接口、链路、日志、指标、告警
执行流程
Step 0：判断当前阶段
收到用户输入后，先判断当前处于哪个阶段：
| 用户意图 | 对应阶段 | 执行路径 |
|---|---|---|
| "分析需求""需求评审" | 阶段 1 需求澄清 | 执行 Step 1 |
| "设计方案""技术评审" | 阶段 2 方案与用例准备 | 执行 Step 2 |
| "写完了""自测""跑测试" | 阶段 3 基础质量验证 | 执行 Step 3 |
| "联调""集成测试""E2E" | 阶段 4 主链路验证 | 执行 Step 4 |
| "专项测试""性能测试" | 阶段 5 专项与性能 | 执行 Step 5 |
| "提测""准备提测""能提测吗" | 阶段 6 提测与回归 | 执行 Step 6（含准入检查） |
| "上线""发布""上线观察" | 阶段 7 上线与观察 | 执行 Step 7 |
| "生成测试用例" | 阶段 3 子任务 | 调用 /gen-testcases command |
| 不确定 | — | 先读代码和 git diff 判断变更范围，再推荐阶段 |
Step 1：需求澄清
开发侧：
- 需求范围明确，边界条件已定义
- 验收标准可量化、可测试
- 风险点已识别并记录
- 依赖项（外部接口、第三方服务）已确认
测试侧：
- 需求已分析，测试范围已圈定
- 高风险场景已标记
- 测试数据需求已明确
输出：需求澄清确认，可进入方案设计。
Step 2：方案与用例准备
开发侧：
- 接口设计已完成（入参、出参、错误码）
- 状态流转已定义
- 异常处理方案已明确
- 并发和回滚方案已考虑
测试侧：
- 测试计划已编写
- 测试用例已覆盖：主流程、异常流程、边界场景
- 用例已按优先级排序（P0 > P1 > P2）
输出：方案和用例就绪，可进入编码。
Step 3：基础质量验证
先确定受影响行为与证据缺口，按需参考 test-levels.md 选择方法；不因变更类型叠加固定测试层级。
可选方法（按证据缺口取最小集合）：
- 静态检查（lint / type check / build）
- 单元测试（核心逻辑的正常/异常/边界路径）
- 模块测试（组件 + 依赖的联动行为）
- 接口/API 测试（契约验证、参数校验、错误码）
生成测试用例：仅在用户要求且具体意图获准时，沿项目已有清单补齐。工具不存在时不要假设可调用 /gen-testcases，也不要因此新建重复清单。
基础质量门禁：
- 编译/构建通过，无语法错误
- 静态检查通过（lint、type check）
- 单元测试通过，核心逻辑覆盖
- 模块测试通过，模块内交互正确
- 接口契约验证通过（如有接口改动）
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +1 lines · -10 tokens per session 1e3e3e59848a
- 1mo ago First seen · 214 lines · 60 tokens per session scan A 6c33f9aa7e2d
devtestops is a skill published in the GitHub repository hexagon-codes/hexclaw-desktop (28 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 2,483 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 2026-08-30.
Other skills, from other repositories
ha-test-strategy
Hope-native test strategy for features, fixes, and refactors: select test-first, regression-first, characterization, integration, E2E, or manual evidence according to risk and repository rules.
ha-verify
Hope-native completion and verification discipline: map each requirement to current direct evidence, choose the smallest sufficient checks, and distinguish proven, failed, blocked, stale, or unverified claims.
ci-speedup
Cuts the wait from push to green by measuring a pipeline's critical path from run timestamps, then splitting, sharding, trimming setup and sharing test module state, with a before/after ledger. Use when asked to "speed up CI", "CI is slow", "why does a PR take 15 minutes", "CI is the bottleneck", or when agents merge…
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
knowledge-engineering-quality-and-delivery
A project-wide quality and delivery workflow covering tests, release checks, builds, publishing, and bilingual documentation for Blade Code.
verify
Pre-merge verification gate. Build, test, and lint must all pass before marking done or shipping.