Subagent Driven Development logo

Subagent Driven Development

Community
ProgrammerAnthony
subagent-driven-development

Use when 已有书面实施计划、任务相对独立,且在本会话内通过子代理逐任务落实时。触发场景:执行实施计划、子代理开发、按计划实现、Task 派发实现、两阶段代码审查、plan execution。

Overview

PublisherProgrammerAnthony
RepositoryExpert-Coding-Harness
Skill namesubagent-driven-development
Stars
236
Forks
77
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ProgrammerAnthony on GitHub. Read the source before you install it.

Installation

Install the Subagent Driven Development AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-Harness.git /tmp/Expert-Coding-Harness
mkdir -p .claude/skills
cp -r /tmp/Expert-Coding-Harness/skills/subagent-driven-development .claude/skills/subagent-driven-development
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Subagent Driven Development in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Subagent Driven Development on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Subagent Driven Development is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

子代理驱动开发

书面实施计划逐任务推进:每个任务派发新的实现子代理(隔离上下文),任务完成后依次做 规格符合性审查 → 代码质量审查(顺序不可颠倒)。主会话负责读计划一次、提取任务全文、协调与决策,不把整段对话历史灌给子代理。

开场声明:「我正在使用子代理驱动开发技能执行计划。」

与「同会话逐步执行」的区别: 本技能强调每任务新子代理 + 双审查;若用户选择在当前会话手写每一步、不用 Task 派子代理,可改按 references/inline-execution-hint.md 配合 tdd-master(TDD 开发大师)code-review-expert(代码审查专家),不再套用下文的 Task 模板。


Inputs / Outputs / Gates / Handoffs(统一契约)

  • Inputs(最小输入):一份书面实施计划(必须包含任务全文:步骤、代码块、命令、预期输出);当前分支/工作目录信息。
  • Outputs(产物形态):按任务推进的执行记录(主会话 Todo 勾选)+ 每任务的 3 段产物:实现结果、规格符合性审查、代码质量审查。
  • Gates(继续前必须满足)
    • 不允许子代理自行打开计划文件代替你粘贴任务全文(除非平台强制且无法粘贴,并需说明风险)。
    • 审查顺序硬门控:先规格符合性审查 → 后代码质量审查
    • 发现阻塞问题必须回到实现修复并复审,通过后才进入下一任务。
  • Handoffs(推荐下游)
    • code-review-expert(代码审查专家):整体收尾审查/质量门禁
    • debug-expert(调试专家):实现或测试失败时切换排查

适用条件

  • 已有实施计划(推荐由 writing-plans(实施计划编写) 产出),任务粒度小、相对独立。
  • 平台支持 Task / 子代理 等派发能力;若不支持,改用同会话执行提示文件。
mermaid
flowchart TD
  A[有实施计划?] -->|否| Z[先完成方案设计与实施计划编写]
  A -->|是| B[任务可独立切片?]
  B -->|否| Y[收紧计划或改人工串行]
  B -->|是| C[本技能: 子代理逐任务]

总流程

  1. 读计划一次,提取全部任务标题与完整任务正文(含步骤、代码块、命令),不要让子代理自己去读计划文件
  2. 用 TodoWrite(或等价方式)列出所有任务,随进度更新。
  3. 对每个任务循环:
    • 派发 实现子代理references/implementer-prompt.md
    • 根据返回状态处理(见下节「实现者状态」)
    • 通过后派发 规格符合性审查references/spec-reviewer-prompt.md
    • 规格 ✅ 后派发 代码质量审查references/code-quality-reviewer-prompt.md,对齐 code-review-expert(代码审查专家) 的严重度与证据要求)
    • 两道审查均未决问题后,勾选任务完成
  4. 全部任务完成后:建议对整体变更再做一次 code-review-expert(代码审查专家) 级别的汇总审查(可再派子代理),并请用户确认合并/PR;若项目后续提供「分支收尾」类技能可再衔接。

实现者状态处理

实现子代理须返回以下之一:

状态处理
DONE进入规格符合性审查
DONE_WITH_CONCERNS先阅读关切;涉及正确性/范围的先处理再审查;仅为观察性备注可记录后继续
NEEDS_CONTEXT补充上下文后重新派发同一任务
BLOCKED缺信息则补上下文;能力不足则换更强模型;任务过大则拆计划;计划错误则上升用户

禁止忽视 BLOCKED、禁止无变更重复派发同模型硬重试。


模型选用(节省成本)

  • 机械实现(1–2 文件、规格完整):较快、较省模型。
  • 多文件集成与判断:标准能力模型。
  • 架构与审查:在可用范围内选最强模型。

提示词模板(必读路径)

文件用途
references/implementer-prompt.md实现子代理
references/spec-reviewer-prompt.md规格符合性审查(先)
references/code-quality-reviewer-prompt.md代码质量审查(后)

派发时将计划中的任务全文粘贴进提示词,并补充场景上下文(依赖、架构位置、工作目录)。


红线(禁止)

  • 未经用户明确同意在 main/master 上开始改代码。
  • 跳过任一审查,或先代码质量、后规格符合(顺序错误)。
  • 并行派发多个实现子代理处理同一仓库同一分支(易冲突)。
  • 让子代理自行打开计划文件代替你粘贴任务全文(除非平台强制且无法粘贴,此时应最小化摘录并说明风险)。
  • 审查发现问题后不修复、不复审就进入下一任务。
  • 用实现者自述替代审查员的独立读码验证。

与项目内技能的衔接

技能作用
writing-plans(实施计划编写)产生本技能消费的勾选式计划
tdd-master(TDD 开发大师)实现与运行测试时应遵循 RED-GREEN-REFACTOR;计划中已拆步骤时以计划为准
code-review-expert(代码审查专家)代码质量审查输出结构与严重度对齐;全量收尾可再显式调用
debug-expert(调试专家)实现或测试失败时切换排查

示例(缩写)

[读取计划 docs/specs/plans/xxx.md,提取任务 1–N 全文,写入 Todo]

任务 1:
  → Task: implementer(全文任务 + 上下文)
  → 实现者 DONE
  → Task: spec reviewer → ✅
  → Task: code quality reviewer → 有 Important 问题 → 实现者修复 → 再审 → ✅
  → 标记任务 1 完成

任务 2:…

全部完成后 → 可选:Task 最终审查 → 用户确认合并

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Subagent Driven Development AI skill do?

Use when 已有书面实施计划、任务相对独立,且在本会话内通过子代理逐任务落实时。触发场景:执行实施计划、子代理开发、按计划实现、Task 派发实现、两阶段代码审查、plan execution。

Why use Subagent Driven Development on TypingMind?

Because you install it once and use it with any model. Subagent Driven Development is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Subagent Driven Development in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ProgrammerAnthony/Expert-Coding-Harness/tree/master/skills/subagent-driven-development. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Subagent Driven Development?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Subagent Driven Development?

As many as you like. As long as a model supports skills, you can use Subagent Driven Development with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Subagent Driven Development AI skill free?

Yes. It is published on GitHub by ProgrammerAnthony under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇