Dispatching Parallel Agents

When you've got multiple independent failures across different test files or subsystems, this cuts debugging time by running separate agents in parallel instead of investigating sequentially. Each agent gets a focused scope like "fix the 3 failures in agent-tool-abort.test.ts" with all necessary context but no shared state. Works well for scenarios like timing issues in one file, API bugs in another, and race conditions in a third. The key is ensuring the problems are actually independent, otherwise agents waste time duplicating work or missing connections between failures.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 6
skills.sh installs: 231.3K
GitHub stars: 315.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add obra/superpowers --skill dispatching-parallel-agents --agent claude-code

Installs into .claude/skills of the current project.

Files

Dispatching Parallel Agents

Overview

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

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

When to Use

digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

SKILL.md on GitHub