Team Composition Patterns

When you're spinning up multiple Claude agents to tackle a task, this gives you the mental model for how many to spawn and what roles they should have. It covers preset configurations like review teams (3 security/performance/architecture reviewers) and debug teams (3 competing hypotheses), plus sizing heuristics that basically say start small because coordination overhead is real. The agent type selection table is the most immediately useful part: it shows which subagent_types have write access versus read-only, so you don't accidentally spawn an Explore agent for implementation work. Also covers tmux versus iTerm2 versus in-process display modes if you're running this locally versus CI.

Install to Claude Code

npx -y skills add wshobson/agents --skill team-composition-patterns --agent claude-code