Subagent Driven Development

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

1,796 stars 164 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development
Manual install
git clone --depth 1 https://github.com/NeoLabHQ/context-engineering-kit.git /tmp/context-engineering-kit
mkdir -p ~/.claude/skills
cp -r /tmp/context-engineering-kit/plugins/sadd/skills/subagent-driven-development ~/.claude/skills/subagent-driven-development

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Subagent-Driven Development

Create and execute plan by dispatching fresh subagent per task or issue, with code and output review after each or batch of tasks.

**Core principle:** Fresh subagent per task + review between or after tasks = high quality, fast iteration.

Executing Plans through agents:

- Same session (no context switch)
- Fresh subagent per task (no context pollution)
- Code review after each or batch of task (catch issues early)
- Faster iteration (no human-in-loop between tasks)

## Supported types of execution

### Sequential Execution

When you have a tasks or issues that are related to each other, and they need to be executed in order, investigating or modifying them sequentially is the best way to go.

Dispatch one agent per task or issue. Let it work sequentially. Review the output and code after each task or issue.

**When to use:**

- Tasks are tightly coupled
- Tasks should be executed in order

### Parallel Execution

When you have multiple unrelated tasks or issues (different files, different subsystems, different bugs), investigatin or modifying them sequentially wastes time. Each task or investigation is independent and can happen in parallel.

Dispatch one agent per independent problem domain. Let them work concurrently.

**When to use:**

- Tasks are mostly independent
- Overral review can be done after all tasks are completed

## Sequential Execution Process

### 1. Load Plan

Read plan file, create TodoWrite with all tasks.
Read the full skill on GitHub

Details

Skill name
subagent-driven-development
Repository
NeoLabHQ/context-engineering-kit
Path
plugins/sadd/skills/subagent-driven-development/SKILL.md
License
GPL-3.0
Repo updated
26 August 2026
Listed in
ComposioHQ/awesome-claude-skills, hesreallyhim/awesome-claude-code, VoltAgent/awesome-agent-skills

FAQ

What does the Subagent Driven Development skill do?

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

How do I install the Subagent Driven Development skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Subagent Driven Development popular?

It lives in NeoLabHQ/context-engineering-kit, which has 1,796 GitHub stars and 164 forks, and is included in 3 curated skill lists.

Related skills

Kaizen

1.8k

NeoLabHQ/context-engineering-kit

Applies continuous improvement methodology. Implement kaizen principles for incremental process improvements.

DevOps & CloudIn 3 lists164

Prompt Engineering

1.8k

NeoLabHQ/context-engineering-kit

Learn and apply prompt engineering techniques and patterns. Master the art of crafting effective prompts for LLMs.

AI, LLMs & AgentsIn 3 lists164

Write Concisely

1.8k

NeoLabHQ/context-engineering-kit

Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.

Writing & ContentIn 3 lists164

Create Ex

2.6k

perkfly/ex-skill

Distill an ex-girlfriend into an AI Skill. Import WeChat/iMessage/SMS/photos, generate Memories + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill，导入微信/iMessage/短信/照片，生成共同记忆 + Persona，支持持续进化。

AI, LLMs & Agents275

LLM Wiki

2.6k

sdyckjq-lab/llm-wiki-skill

个人知识库构建系统（基于 Karpathy llm-wiki 方法论）。让 AI 持续构建和维护你的知识库， 支持多种素材源（网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件）， 自动整理为结构化的 wiki。 触发条件：用户明确提到"知识库"、"wiki"、"llm-wiki"，或要求对已初始化的知识库执行 消化、查询、健康检查等操作。不要在用户只是要求"总结这篇文章"时触发——必须是明确的 知识库相关意图。

AI, LLMs & Agents301

Claude to Im

2.9k

op7418/Claude-to-IM-skill

Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to-im", "bridge", "消息推送", "消息转发", "桥接", "连上飞书", "手机上看claude", "启动后台服务", "诊断", "查看日志", "配置". Subcommands: setup, start, stop, status, logs, reconfigure, doctor. Do NOT use for: building standalone bots, webhook integrations, or coding with IM platform SDKs — those are regular programming tasks.

AI, LLMs & Agents315

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.