Verified:GitHub

superpowers-subagent

Dispatch a fresh subagent per task and apply two-stage reviews.

Updated Apr 4, 2026

Search Tags:#subagents #code-quality #plan-execution #two-stage-review #parallel-processing #task-dispatch #agent-orchestration

Ready to run

npx skills add https://github.com/susantosanto/config-opencode --skill superpowers-subagent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: superpowers-subagent
Source: https://github.com/susantosanto/config-opencode/tree/main/skills/superpowers-subagent
Command: npx skills add https://github.com/susantosanto/config-opencode --skill superpowers-subagent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating plan execution across multiple AI tasks can lead to context pollution and bottlenecks. This skill provides a disciplined workflow by dispatching a fresh subagent per task, ensuring isolated execution and faster iteration.

Core Features & Use Cases

Fresh subagent per task to avoid context bleed and enable focused work.
Two-stage review: specification alignment first, then code quality validation, with iterative feedback loops.
End-to-end task handling: planning, implementing, testing, and review within a single session.
Use Case: when implementing a multi-step feature, spawn per-step subagents, review results, and merge into final code.

Quick Start

Dispatch a fresh subagent for each task and perform two-stage reviews to validate spec compliance and code quality.

Frequently Asked Questions about superpowers-subagent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I coordinate subagents for parallel task execution without context pollution?▼

To coordinate parallel task execution without context pollution, dispatch a fresh subagent for each task. This isolates execution, prevents context bleed, and enables focused work for faster iteration across multiple steps.

What is a two-stage review process for AI-generated code?▼

A two-stage review process validates AI-generated code by first confirming specification alignment, then validating code quality. This iterative feedback loop ensures the implementation meets requirements and maintains standards before final integration.

How do I implement multi-step features by dispatching subagents per task?▼

To implement multi-step features, dispatch a fresh subagent per task to handle planning, implementation, testing, and self-review. Apply a two-stage review to confirm spec compliance and code quality before merging the final code.

Can I handle planning, testing, and code review within a single agent session?▼

Yes, you can handle end-to-end task execution within a single session. By dispatching isolated subagents per task, each agent handles its own planning, implementing, testing, and self-review before final integration.

Why does context bleed happen in agent orchestration and how to avoid it?▼

Context bleed happens in agent orchestration when multiple tasks share the same context window, causing bottlenecks. Avoid it by dispatching a fresh subagent per task to ensure isolated execution and maintain focused iteration.