👥
AI EngineeringPython

Team Composition Patterns

by wshobson

Team Composition Patterns is an AI Engineering skill for Claude Code, published by wshobson in agents.

38.8K stars4.1K forkson wshobson/agentsAdded 2026/08/13Repository updated 2026/08/05
View source on GitHubDownload repo ZIP
agent-skillsagentic-aiagentsai-agentsanthropicautomationclaude-codeclaude-code-pluginscodex-clicopilotcursorcursor-rulesdeveloper-toolsgemini-climcpmulti-agentopencodeorchestrationprompt-engineeringworkflows
Install in seconds
Install Team Composition Patterns
Copy Team Composition Patterns into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/wshobson/agents/tree/main/plugins/agent-teams/skills/team-composition-patterns ~/.claude/skills/team-composition-patterns

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/wshobson/agents.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
plugins/agent-teams/skills/team-composition-patterns/SKILL.md in wshobson/agents
Installs to
~/.claude/skills/team-composition-patterns
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering — 2451 skills

What Team Composition Patterns does

Team Composition Patterns provides heuristics and preset configurations for designing multi-agent teams in Claude Code, covering team sizing, agent type selection, and display modes. Use it when deciding how many agents to spawn, choosing between review, feature, or debug teams, or configuring teammate display modes.

Team Composition Patterns is cataloged under AI Engineering on DirSkills. Team Composition Patterns comes from a repository tagged agent-skills, agentic-ai, agents, ai-agents and anthropic.

Documentation

README

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

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Team Composition Patterns

  • What else does wshobson publish alongside Team Composition Patterns?

    Team Composition Patterns is one of 25 skills that DirSkills catalogs from wshobson/agents, the repository it ships in. Its siblings there include API Design Principles, Architecture Patterns and Before You Build. Each one is a separate skill with its own page in this directory, installs the same way Team Composition Patterns does, and is maintained by wshobson in that same repository. The rest of the collection is listed on the wshobson/agents page.

  • How does Team Composition Patterns compare to other AI Engineering skills?

    Team Composition Patterns ranks #130 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Team Composition Patterns against them. Open each page to compare what they document and how they install.

More from wshobson/agents

Team Composition Patterns is one of 25 skills cataloged on DirSkills from wshobson/agents.

See all 25 skills →
🔌
3w ago

API Design Principles

API Design Principles covers REST and GraphQL API design patterns, versioning strategies, and best practices for building intuitive, scalable, maintainable APIs. Use it when designing new APIs, reviewing API specifications, or establishing API design standards.
DevOps
38.8K4.1K
🏗️
3w ago

Architecture Patterns

Architecture Patterns provides patterns for Clean Architecture, Hexagonal Architecture, and Domain-Driven Design to build maintainable, testable, and scalable backend services. Use it when designing new services, refactoring monoliths, establishing bounded contexts, or debugging dependency cycles.
DevOps
38.8K4.1K
🚦
3w ago

Before You Build

Before You Build reviews product and feature ideas before implementation to identify the highest-risk assumption and the smallest validation step for MVPs, landing pages, SaaS products, internal tools, agent workflows, or major features.
Quality
38.8K4.1K
🛡️
3w ago

Block No-Verify Hook

Block No-Verify Hook configures a PreToolUse hook in Claude Code settings to block git commands that include bypass flags like --no-verify and --no-gpg-sign. Use it when setting up projects that enforce commit quality gates and want to prevent AI agents from skipping pre-commit hooks.
AI Engineering
38.8K4.1K
🎨
3w ago

Brand Landing Page

Brand Landing Page runs a brand-identity interview covering colors, typography, and shape language, then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use it when building a landing page, homepage, or marketing page without an established visual direction.
Frontend
38.8K4.1K
🔀
3w ago

CQRS Implementation

CQRS Implementation guides separating read and write models for scalable architectures and event-sourced systems. Use it when you need to scale reads and writes independently, optimize query performance, or implement high-performance reporting.
DevOps
38.8K4.1K

More AI Engineering skills

Team Composition Patterns is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #130 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K