subagent-driven-development

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.

509 stars

Best use case

subagent-driven-development is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.

Teams using subagent-driven-development should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/subagent-driven-development/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/superpowers/skills/subagent-driven-development/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/subagent-driven-development/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How subagent-driven-development Compares

Feature / Agentsubagent-driven-developmentStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Subagent-Driven Development

## Overview

Execute plan by dispatching fresh subagent per task with two-stage review: spec compliance first, then code quality.

**Core principle:** Fresh subagent per task + two-stage review = high quality, fast iteration.

## When to Use

- Have implementation plan with mostly independent tasks
- Want to stay in current session
- Want automatic review checkpoints

## Two-Stage Review

1. **Spec Compliance** - Did they build what was requested? (nothing more, nothing less)
2. **Code Quality** - Is it well-built? (clean, tested, maintainable)

Spec MUST pass before quality review begins.

## Red Flags

- Never skip either review stage
- Never proceed with unfixed issues
- Never dispatch multiple implementation subagents in parallel
- Never let implementer self-review replace actual review

## Agents Used

- `agents/implementer/` - Fresh subagent per task
- `agents/spec-reviewer/` - Verifies spec compliance
- `agents/code-quality-reviewer/` - Verifies code quality
- `agents/code-reviewer/` - Final review of entire implementation

## Tool Use

Invoke via babysitter process: `methodologies/superpowers/subagent-driven-development`

Related Skills

vue-development

509
from a5c-ai/babysitter

Vue 3 development with Composition API, reactivity system, component patterns, TypeScript integration, and best practices.

react-development

509
from a5c-ai/babysitter

Specialized skill for React component development, hooks patterns, state management, context API, performance optimization, and modern React best practices.

angular-development

509
from a5c-ai/babysitter

Angular development patterns including modules, components, services, dependency injection, signals, and enterprise architecture.

REPL Development

509
from a5c-ai/babysitter

Expert skill for building interactive REPLs with rich editing and evaluation features

Swift/SwiftUI Development

509
from a5c-ai/babysitter

Expert skill for native iOS development with Swift and SwiftUI

React Native Development

509
from a5c-ai/babysitter

Deep integration with React Native ecosystem for cross-platform mobile development

Kotlin/Jetpack Compose Development

509
from a5c-ai/babysitter

Expert skill for native Android development with Kotlin and Jetpack Compose

Flutter/Dart Development

509
from a5c-ai/babysitter

Specialized skill for Flutter app development and Dart programming

unreal-development

509
from a5c-ai/babysitter

Unreal Engine integration skill for C++/Blueprint development, actor lifecycle management, plugin development, and editor automation. Enables LLMs to interact with Unreal Editor through MCP servers for level manipulation, Blueprint generation, and automated workflows.

unity-development

509
from a5c-ai/babysitter

Unity Engine integration skill for project setup, C# scripting, scene management, prefab creation, and editor automation. Enables LLMs to interact with Unity Editor through MCP servers for asset manipulation, script generation, and automated workflows.

godot-development

509
from a5c-ai/babysitter

Godot Engine integration skill for GDScript/C# development, scene composition, node management, and editor automation. Enables LLMs to interact with Godot Editor through MCP servers for asset manipulation, script generation, and automated workflows.

assessment-item-development

509
from a5c-ai/babysitter

Create valid, reliable assessment items across formats (multiple choice, constructed response, performance tasks) following psychometric best practices