subagent-driven-development

Dispatch fresh subagents per task with two-stage review (spec compliance, then code quality) in the current session.

obra ↓ 154k
Claude Code
View source ↗

What it does

  • Same session (no context switch)
  • Fresh subagent per task (no context pollution)
  • Review after each task (spec compliance + code quality), broad review at the end
  • Faster iteration (no human-in-loop between tasks)
  • tasks that contradict each other or the plan's Global Constraints
  • anything the plan explicitly mandates that the review rubric treats as a
  • Touches 1-2 files with a complete spec → cheap model

Requirements & configuration

  • diff's size, complexity, and risk. A small mechanical diff does not need the
  • Turn count beats token price. Wall-clock and context cost scale with how
  • Requires design judgment or broad codebase understanding → most capable model
  • NEEDSCONTEXT: The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.
  • 2. If the task requires more reasoning, re-dispatch with a more capable model

Configuration: HEAD

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

Dispatch fresh subagents per task with two-stage review (spec compliance, then code quality) in the current session.

Source

Repository: https://github.com/obra/superpowers

subagent-driven-development FAQ

What does the subagent-driven-development skill do?

Use when executing implementation plans with independent tasks in the current session Same session (no context switch) Fresh subagent per task (no context pollution)

What does subagent-driven-development require?

diff's size, complexity, and risk. A small mechanical diff does not need the Turn count beats token price. Wall-clock and context cost scale with how Requires design judgment or broad codebase understanding → most capable model NEEDSCONTEXT: The implementer needs information that wasn't provided. Provide the missing context and re-dispatch. 2. If the task requires more reasoning, re-dispatch with a more capable model Configuration keys: HEAD.

How do I install subagent-driven-development?

Run: npx -y skills add https://github.com/obra/superpowers --skill subagent-driven-development --agent claude-code — the source lives at github.com/obra/superpowers.

Maintain subagent-driven-development?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

subagent-driven-development on getagentictools
[![subagent-driven-development on getagentictools](https://getagentictools.com/badge/skills/obra-superpowers-subagent-driven-development.svg)](https://getagentictools.com/skills/obra-superpowers-subagent-driven-development?ref=badge)
npx agentictools info skills/obra-superpowers-subagent-driven-development

The second line is the CLI lookup for this page — handy in READMEs and docs.