tech-plan

A skill for producing technical plan documents from requirements and clarification records. It describes expected behavior, acceptance checks, tasks, boundaries, dependencies, and unresolved questions.

In plain words
What is it for?
Use it during the fourth step of the dev-flow process to create a Markdown plan for each task, including goals, acceptance criteria, task breakdown, dependencies, and status.
Why use it?
It gives each development task a consistent, testable plan before implementation begins.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/today-hbw/claude-code-dev-workflow/tech-plan
Any agent
npx skills add Today-Hbw/claude-code-dev-workflow --skill tech-plan
Clone the repo
git clone --depth 1 https://github.com/Today-Hbw/claude-code-dev-workflow

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 526851fa4a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/dev-flow/skills/tech-plan/SKILL.md · 97 lines

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

  1. 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"
  2. 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"
  3. 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
  4. 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"
  5. 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
  6. 头部署名:头部「负责人」取第 0 步解析出的个人标识(person

  7. 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
Changes

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.

  1. 2d ago First seen · 97 lines · 29 tokens per session scan A 526851fa4a11

Subscribe to this mod's changes

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.

Related

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…

comet-ml/opik · 93 tokens

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.

kangarooking/cangjie-skill · 136 tokens

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。.

zenstory-ai/drama-skills · 102 tokens

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.

Emily2040/seedance-2.0 · 68 tokens

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。.

devcxl/mattpocock-skills-zh · 43 tokens

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…

AnastasiyaW/codex-claude-code-config · 166 tokens