Multi Agent Patterns

When you hit context limits on complex tasks, this walks you through splitting work across multiple Claude instances. It covers three patterns: supervisor (central coordinator delegates to specialists), peer-to-peer (agents hand off directly via function returns), and hierarchical (layered abstraction). The big insight here is that multi-agent systems aren't about simulating teams, they're about context isolation. Fair warning though, token costs jump to roughly 15x compared to single-agent approaches, so you're trading money for capability. The skill includes a practical fix for the "telephone game" problem where supervisors mangle sub-agent responses, using a forward_message pattern that lets specialists respond directly to users.

skills.sh installs: 390
GitHub stars: 39.4K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill multi-agent-patterns --agent claude-code

Installs into .claude/skills of the current project.

Files

Multi-Agent Architecture Patterns

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.