Subagent Driven Development

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

a5c-ai Updated 1.7k repo stars

File contents

  • 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

a5c-ai/babysitter/tree/main/library/methodologies/superpowers/skills/subagent-driven-development commit 71ca2a0abf

Frequently asked questions

npx skillmds@latest add a5c-ai/subagent-driven-development