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/tech-plannpx skills add Today-Hbw/claude-code-dev-workflow --skill tech-plangit 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 | $0.00029 | $0.01227 |
| Opus 5 | $0.00015 | $0.00613 |
| Sonnet 5 | $0.00006 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
tech-plan 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
技术方案 · 输出格式
你的任务
为每个任务生成 计划.md 技术方案文档,写入输出目录。方案要行为化:描述系统应该做什么,而不是怎么做。
输出格式
参考以下模板生成每个任务的 计划.md:
# <任务名称>(IDxxxxxxx)· 计划
> 父需求:<所属大需求> | 负责人:<人名>
> 依赖:<关键依赖说明>
## 目标
<1-3 句话说清楚这个任务要做什么,用行为化描述>
## 验收标准
- [ ] <具体、可测试的条目 1>
- [ ] <具体、可测试的条目 2>
- [ ] <具体、可测试的条目 3>
<!-- 若需求含视觉规格(PRD 截图/原型已定死位置或文案),逐条列为可勾选项,照图写死。以下为示例,按本需求替换或删除: -->
<!-- - [ ] <字段>折进已有列<列名>作为第 N 行,不新建独立列 -->
<!-- - [ ] <按钮>文案精确为<原文>,位于<页签>工具栏、紧挨<相邻按钮> -->
<!-- - [ ] <筛选A><筛选B>与现有筛选并列 -->
## 任务拆解
1. **<子任务 1 名称>**(`<涉及的模块/接口>`):<行为描述>
- 实现要点:<关键逻辑,用接口/类型描述,不写文件路径>
2. **<子任务 2 名称>**(`<涉及的模块/接口>`):<行为描述>
- 实现要点:<关键逻辑>
## 边界 / 依赖
- **不做的事(作用域外)**:
- <明确列出不实现的功能>
- **外部依赖**:
- <依赖的接口/表/配置>
- **需要配合的事项**:
- <需要其他人做的事>
## 待确认
- <仅列 PRD 图与正文都未给出的开放项>
> 判定(图已定 vs 真待确认):位置/文案凡 PRD 图或正文已给出,一律按图写进验收标准,不进本节;只有两处都没写才算真待确认。
## 状态:进行中
格式要求
-
行为化描述:目标和验收标准描述系统应该做什么,不描述实现过程
- ✅ 好例子:"运行
npm test时,所有关于用户偏好的测试通过" - ❌ 坏例子:"代码要写好"
- ✅ 好例子:"接口返回
{ preferences: Preference[] },空数组表示无偏好" - ❌ 坏例子:"在 src/api/user.ts 第 42 行加一个函数"
- ✅ 好例子:"运行
-
避免写死文件路径和行号:任务拆解用模块名/接口名描述,不用具体路径
- 文件路径会随重构过时,接口描述更稳定
- 如果某段代码精确到无法用文字描述(如状态机、Schema),可以内联代码片段并注明"来自原型"
-
视觉规格按图写死:需求含 PRD 截图/原型时,把其中已定死的元素(视觉规格五要素:列归属/合并、按钮精确文案、所在页签、筛选位置、字段顺序)逐条写进验收标准,文案与页签名照抄 PRD 图,不自拟
- 这与「避免写死文件路径」不冲突:路径是会过时的实现细节,UI 位置/文案是需求本身
-
验收标准要具体可测:每条标准独立可验证
- ✅ 好例子:"空输入时,接口返回 400 并包含
message: '不能为空'" - ❌ 坏例子:"错误处理要正确"
- ✅ 好例子:"空输入时,接口返回 400 并包含
-
作用域外要明确:防止执行时越界
- 列出"不做什么"和"不在本次范围"的事项
-
头部署名:头部「负责人」取第 0 步解析出的个人标识(
person) -
状态:初始为「进行中」,完成后改为「已完成(详见 ../总结.md)」
写入规则
- 文件路径:
<session_dir>/<任务简称_ID>/计划.md - 任务简称从 PRD 中提取,不超过 10 个字
- 目录不存在时自动创建
- 编码:UTF-8
注意事项
- 方案要基于 QA 记录中的结论,不要和 QA 矛盾
- 涉及数据库变更的,Schema 描述可以用代码片段内联(这是允许的例外)
- 涉及接口变更的,接口形状用代码片段描述(也是允许的例外)
- 如果发现方案有困难,主动和用户沟通调整
- 写完后用 AskUserQuestion 向用户确认方案
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 · 97 lines · 29 tokens per session scan A 526851fa4a11
tech-plan is a skill published in the GitHub repository Today-Hbw/claude-code-dev-workflow (22 stars, last pushed 21d ago), licensed MIT. It adds 29 tokens to every session and 1,227 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.
setup-matt-pocock-skills
为本仓库配置工程技能——设置其 issue tracker、分诊标签词汇表和领域文档布局。首次使用其他工程技能前运行一次。.
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…