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/today-hbw/claude-code-dev-workflow/self-testnpx skills add Today-Hbw/claude-code-dev-workflow --skill self-testgit clone --depth 1 https://github.com/Today-Hbw/claude-code-dev-workflowWhat 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 | $0.00026 | $0.01170 |
| Opus 5 | $0.00013 | $0.00585 |
| Sonnet 5 | $0.00005 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
self-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 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.
What it actually says
自测 · 检查清单
你的任务
编码完成后,按照以下清单逐项检查,确保代码质量。
测试哲学
在检查之前,先确认测试本身的质量:
好测试的特征:
- 通过公共接口验证行为,不关心内部实现
- 读起来像规格说明:"用户可以带着有效购物车结算"
- 内部重构后依然通过(测试的是"做什么",不是"怎么做")
坏测试的特征:
- mock 内部协作者、测试私有方法
- 改了内部函数名就挂,但行为没变
- 描述的是实现细节而非用户可见行为
警告信号:如果你的测试在重构后失败,但行为没变,说明测试在测实现而非行为。
检查清单
1. 功能验证
- 每个任务的核心功能是否实现(对照计划.md 的验收标准逐条检查)
- 是否覆盖了 QA 中提到的所有场景
- 边界条件是否处理(空值、极值、异常输入)
- 错误提示是否友好(用户能看到有意义的错误信息)
2. 数据一致性
- 数据库字段是否与 Schema 描述一致
- 新增/修改/删除操作是否完整
- 数据流转是否正确(从输入到存储到展示)
3. 依赖检查
- 外部依赖(接口、表、配置)是否就绪
- 依赖的字段/列是否存在
- 同步任务/ETL 是否需要配合
4. 代码质量
- 是否有遗留的 TODO 或调试代码
- 命名是否清晰(变量、函数、文件)
- 注释是否充分(复杂逻辑处)
- 是否有重复代码可以提取
5. 兼容性
- 是否与现有功能兼容(不破坏已有逻辑)
- 接口变更是否有向后兼容处理
6. 测试质量
- 测试是否通过公共接口验证行为
- 测试是否能扛住内部重构(重命名内部函数不应让测试挂掉)
- 是否避免了横向切片(不要先批量写所有测试,再批量写所有实现)
- 测试命名是否描述了行为而非实现("用户可以结算"而非"调用了 processOrder 函数")
7. 视觉规格核对(对照 PRD 截图/原型)
仅当本次涉及 UI 时执行。基准是 PRD 原图,不因 计划.md 未写而跳过——上游可能漏抽截图规格。
- 字段列归属:新增字段折进已有列还是独立列,与截图一致
- 字段/筛选顺序:同一列或区域内排列顺序与截图一致
- 按钮/入口文案:与截图逐字一致,未自拟或改写
- 所在容器:按钮/筛选挂在截图指定的页签/工具栏,未擅自新建页签或区域
- 筛选项位置:与截图中现有筛选的并列关系一致
- 若实现与截图不符:修正实现,不改截图规格
反模式警示
横向切片(要避免)
❌ 错误方式:
RED: test1, test2, test3, test4, test5 ← 批量写测试
GREEN: impl1, impl2, impl3, impl4, impl5 ← 批量写实现
正确方式(垂直切片):
test1→impl1 → test2→impl2 → test3→impl3 → ...
批量写的测试测的是想象中的行为,而不是实际实现的行为。每个测试应该是对前一轮实现的响应。
输出格式
## 自测结果
### ✅ 通过项
- <通过的检查项>
### ⚠️ 需注意
- <需要关注但不是阻塞的问题>
### ❌ 阻塞项
- <必须修复才能继续的问题>
注意事项
- 如果有阻塞项,回到步骤 5 修复后再继续
- 重点检查计划.md 中的验收标准是否全部满足
- 涉及 UI 时,位置/文案以 PRD 截图为准;计划.md 若与截图冲突或漏写,回原图核对并按图修正
- 测试质量检查重点看公共接口,不深入内部实现
- 自测不需要跑性能测试(除非计划.md 中明确要求)
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 First seen · 117 lines · 26 tokens per session scan A 496b043ba38d
self-test is a skill published in the GitHub repository Today-Hbw/claude-code-dev-workflow (22 stars, last pushed 21d ago), licensed MIT. It adds 26 tokens to every session and 1,170 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
short-drama-storyboard
把剧本和视觉事实转成有镜头职责、空间连续性和可冻结起点的 剧集/ /分镜.md。 每镜使用二级标题 ## SHOT-...,同镜下用 ### 冻结关键帧提示词 写起始帧正文。.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
deep-review
Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCEPT triage. Use…
frontend-design
Создание высококачественных, визуально выдающихся фронтенд-интерфейсов. Используй ВСЕГДА когда пользователь просит создать веб-страницу, компонент, лендинг, дашборд, UI-кит, форму, карточки, навигацию, анимации, или любой другой веб-интерфейс. Скилл покрывает: HTML/CSS/JS компоненты, React/Vue/Svelte, Tailwind CSS…