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.

skills.sh installs: 10K
GitHub stars: 42.4K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Team Composition Patterns

Best practices for composing multi-agent teams, selecting team sizes, choosing agent types, and configuring display modes for Claude Code's Agent Teams feature.

When to Use This Skill

Deciding how many teammates to spawn for a task
Choosing between preset team configurations
Selecting the right agent type (subagent_type) for each role
Configuring teammate display modes (tmux, iTerm2, in-process)
Building custom team compositions for non-standard workflows

Team Sizing Heuristics

Complexity	Team Size	When to Use
Simple	1-2	Single-dimension review, isolated bug, small feature
Moderate	2-3	Multi-file changes, 2-3 concerns, medium features
Complex	3-4	Cross-cutting concerns, large features, deep debugging
Very Complex	4-5	Full-stack features, comprehensive reviews, systemic issues