building-agent-team-prompts

SKILL.md

Agent team prompts must be self-contained — teammates don't inherit your conversation history. Every piece of context a teammate needs must be in their spawn prompt or discoverable from the codebase.

Core principle: A good agent team prompt specifies WHO does WHAT on WHICH files, HOW they communicate, and WHEN they're done.

Don't use agent teams for: sequential tasks, work concentrated in a few files, or simple tasks where coordination overhead exceeds benefit. Use subagents or a single session instead.

Provides a prompt template and best practices for building Claude Code agent teams. Covers team composition, teammate spawn prompts, task breakdown, file ownership, communication protocols, and delegate mode. Use when creating an agent team, spawning teammates, parallelizing work across multiple Claude Code instances, or deciding whether an agent team is the right approach. Source: frontboat/agent-teams.

View raw