🎯

team-composition-patterns

🎯Skill

Helps you decide how many AI helper agents to put on a task and what role each one plays. It offers ready-made team setups for reviewing, debugging, building features, research, security checks and migrations in Claude Code's Agent Teams.

wshobson/agents7,201 InstallsAdded Feb 6, 2026

Installation

$npx skills add wshobson/agents --skill team-composition-patterns

Run it in a terminal; it asks which AI coding tools to install it for (Claude Code, Codex, Cursor and more).

Uses skills.sh Β· Node.js 22.20+

After installing

Ask for related work and the agent uses it on its own, or call it yourself.

Run it (Claude Code)/team-composition-patterns
Install by hand

Copy the whole skill folder from GitHub to the place below. Copying only SKILL.md can leave out files the skill uses.

Open the skill folder β†’
  • This project .claude/skills/team-composition-patterns/
  • All projects ~/.claude/skills/team-composition-patterns/

These paths are for Claude Code. For other tools, the command above puts it in the right place.

What this skill does

Overview

This skill helps you plan a team of AI agents in Claude Code's Agent Teams feature. An agent here is an AI helper that works on one part of a job. The skill tells you how many to use, which type to pick for each role, and how to show them on screen.

Key Features

  • Pick a team size from 1 to 5 based on how complex the task is.
  • Use ready-made teams for review, debugging, features, app-wide features, research, security and migrations.
  • Choose the right agent type so each helper has the tools it needs, such as permission to edit files.
  • Set how teammates appear: in tmux panes (a tool that splits your terminal), iTerm2 tabs, or one shared process.
  • Fix common problems, like helpers repeating each other's work or not receiving tasks.

Who is this for?

This is for Claude Code users who want several agents to work on one task at the same time. It helps most when you are unsure how to split the work. Small teams of 2 to 4 are usually the best start.

Summarized by AI from this skill's SKILL.md. Suggest a better one

Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to spawn for a task, when choosing between a review team versus a feature team versus a debug team, when selecting the correct subagent_type for each role to ensure agents have the tools they need, when configuring display modes (tmux, iTerm2, in-process) for a CI or local environment, or when building a custom team composition for a non-standard workflow such as a migration or security audit.

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

ComplexityTeam SizeWhen to Use
Simple1-2Single-dimension review, isolated bug, small feature
Moderate2-3Multi-file changes, 2-3 concerns, medium features
Complex3-4Cross-cutting concerns, large features, deep debugging
Very Complex4-5Full-stack features, comprehensive reviews, systemic issues

Rule of thumb: Start with the smallest team that covers all required dimensions. Adding teammates increases coordination overhead.

Preset Team Compositions

Review Team

  • Size: 3 reviewers
  • Agents: 3x team-reviewer
  • Default dimensions: security, performance, architecture
  • Use when: Code changes need multi-dimensional quality assessment

Debug Team

  • Size: 3 investigators
  • Agents: 3x team-debugger
  • Default hypotheses: 3 competing hypotheses
  • Use when: Bug has multiple plausible root causes

Feature Team

  • Size: 3 (1 lead + 2 implementers)
  • Agents: 1x team-lead + 2x team-implementer
  • Use when: Feature can be decomposed into parallel work streams

Fullstack Team

  • Size: 4 (1 lead + 3 implementers)
  • Agents: 1x team-lead + 1x frontend team-implementer + 1x backend team-implementer + 1x test team-implementer
  • Use when: Feature spans frontend, backend, and test layers

Research Team

  • Size: 3 researchers
  • Agents: 3x general-purpose
  • Default areas: Each assigned a different research question, module, or topic
  • Capabilities: Codebase search (Grep, Glob, Read), web search (WebSearch, WebFetch)
  • Use when: Need to understand a codebase, research libraries, compare approaches, or gather information from code and web sources in parallel

Security Team

  • Size: 4 reviewers
  • Agents: 4x team-reviewer
  • Default dimensions: OWASP/vulnerabilities, auth/access control, dependencies/supply chain, secrets/configuration
  • Use when: Comprehensive security audit covering multiple attack surfaces

Migration Team

  • Size: 4 (1 lead + 2 implementers + 1 reviewer)
  • Agents: 1x team-lead + 2x team-implementer + 1x team-reviewer
  • Use when: Large codebase migration (framework upgrade, language port, API version bump) requiring parallel work with correctness verification

Agent Type Selection

When spawning teammates with the Agent tool, choose subagent_type based on what tools the teammate needs:

Agent TypeTools AvailableUse For
general-purposeAll tools (Read, Write, Edit, Bash, etc.)Implementation, debugging, any task requiring file changes
ExploreRead-only tools (Read, Grep, Glob)Research, code exploration, analysis
PlanRead-only toolsArchitecture planning, task decomposition
agent-teams:team-reviewerRead/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessageCode review with structured findings
agent-teams:team-debuggerRead/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessageHypothesis-driven investigation
agent-teams:team-implementerRead/Write/Edit/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessageBuilding features within file ownership boundaries
agent-teams:team-leadRead/search/Bash plus Agent Teams coordination toolsTeam orchestration and coordination

Key distinction: Read-only agents (Explore, Plan) cannot modify files. Never assign implementation tasks to read-only agents.

Display Mode Configuration

Configure in ~/.claude/settings.json:

{
  "teammateMode": "tmux"
}
ModeBehaviorBest For
"tmux"Each teammate in a tmux paneDevelopment workflows, monitoring multiple agents
"iterm2"Each teammate in an iTerm2 tabmacOS users who prefer iTerm2
"in-process"All teammates in same processSimple tasks, CI/CD environments

Custom Team Guidelines

When building custom teams:

  1. Every team needs a coordinator β€” Either designate a team-lead or have the user coordinate directly
  2. Match roles to agent types β€” Use specialized agents (reviewer, debugger, implementer) when available
  3. Avoid duplicate roles β€” Two agents doing the same thing wastes resources
  4. Define boundaries upfront β€” Each teammate needs clear ownership of files or responsibilities
  5. Keep it small β€” 2-4 teammates is the sweet spot; 5+ requires significant coordination overhead

Troubleshooting

A teammate was spawned as Explore but needs to write files. Explore and Plan are read-only agents. Change the subagent_type to general-purpose or an appropriate specialized agent type. Never assign implementation tasks to read-only agents.

The team is growing too large and coordination is slowing everything down. Each additional teammate adds communication overhead. Consolidate roles: can one agent cover two dimensions? A 4-person team doing 6 independent tasks is usually better served by 3 agents covering 2 tasks each.

tmux mode is not showing panes. Ensure tmux is installed and a session is already running before spawning teammates. The in-process mode works without tmux and is suitable for CI or scripted environments.

Two reviewers are flagging the same issues. The review dimensions overlap. Redefine each reviewer's focus area: one on correctness/logic, one on security, one on performance/scalability. Overlapping coverage wastes tokens and produces duplicate findings.

A team-lead is spawning teammates but they are not receiving tasks. Verify that the lead is using the Agent tool to spawn teammates and passing complete context in the prompt. Teammates start fresh with no prior conversation history β€” they need all relevant information in their initial prompt.

Related Skills

More from this repository10

🎯
tailwind-design-system🎯Skill

Helps you build a consistent look for your app with Tailwind CSS v4. It sets up shared colors, sizes, dark mode and reusable components so every screen matches.

🎯
typescript-advanced-types🎯Skill

A guide to TypeScript's advanced type features, which describe the shape of your data so mistakes are caught before the code runs. It covers reusable types, types that change based on rules, and built-in helper types, with short examples.

🎯
nodejs-backend-patterns🎯Skill

Guidance for building reliable server-side apps with Node.js, using Express or Fastify. It covers login, error handling, databases, API design and a list of proven best practices.

πŸͺ
wshobson-agentsπŸͺMarketplace

Intelligent automation and multi-agent orchestration for Claude Code

πŸ”Œ
framework-migrationπŸ”ŒPlugin

Claude Code plugin for AI-powered framework migration workflows, coordinating specialized agents to plan and execute transitions between technology stacks as part of the wshobson/agents marketplace.

πŸ”Œ
payment-processingπŸ”ŒPlugin

A Claude Code plugin for payment system integration covering Stripe, PayPal, and billing platforms with checkout flows, subscription management, and webhook handling in the wshobson/agents ecosystem.

πŸ”Œ
developer-essentialsπŸ”ŒPlugin

A Claude Code plugin bundling core development tools and agents for everyday tasks like debugging and code generation, part of the wshobson/agents marketplace with 73 focused plugins.

πŸ”Œ
observability-monitoringπŸ”ŒPlugin

Claude Code plugin for observability and monitoring including logging, metrics, distributed tracing, and alerting, part of the wshobson/agents marketplace with 73 focused plugins.

πŸ”Œ
deployment-strategiesπŸ”ŒPlugin

A Claude Code plugin providing specialized AI agents for deployment strategy planning and execution, covering blue-green deployments, canary releases, rolling updates, and zero-downtime patterns.

πŸ”Œ
jvm-languagesπŸ”ŒPlugin

Claude Code plugin for JVM language development including Java, Kotlin, and Scala with specialized agents for idiomatic patterns, build tools, and runtime optimization in the wshobson/agents marketplace.