PluginBench
Skill
Review
Audit score 70

team-composition-patterns

wshobson/agents

Design optimal multi-agent team compositions with sizing heuristics, preset configurations, and agent type selection.

What is team-composition-patterns?

This skill provides best practices for composing Claude Code Agent Teams, including team sizing heuristics (1–5 agents based on complexity), preset configurations for common workflows (review, debug, feature, fullstack, research, security, migration teams), and guidance on selecting the right agent type for each role. Use it when deciding team size, choosing between preset team patterns, selecting subagent_type for specialized roles, configuring display modes, or building custom team compositions.

  • Apply team sizing heuristics based on task complexity (simple 1–2 agents, moderate 2–3, complex 3–4, very complex 4–5)
  • Select from seven preset team compositions: Review, Debug, Feature, Fullstack, Research, Security, and Migration teams
  • Match agent types to required capabilities: general-purpose, Explore, Plan, team-reviewer, team-debugger, team-implementer, team-lead
  • Configure teammate display modes (tmux, iTerm2, in-process) for different environments
  • Define clear role boundaries and file ownership to minimize coordination overhead
  • Troubleshoot common team composition issues: read-only agent limitations, coordination overhead, overlapping reviewer coverage

How to install team-composition-patterns

npx skills add https://github.com/wshobson/agents --skill team-composition-patterns
Claude Code
Cursor
Windsurf
Cline

How to use team-composition-patterns

  1. 1.Assess task complexity (simple, moderate, complex, very complex) to determine team size
  2. 2.Select a preset team composition matching your workflow (review, debug, feature, fullstack, research, security, migration) or design a custom team
  3. 3.Choose the correct subagent_type for each role based on required tools (general-purpose for implementation, Explore/Plan for read-only research, specialized agents for review/debug/implementation)
  4. 4.Configure display mode in ~/.claude/settings.json (tmux for development, in-process for CI/CD)
  5. 5.Define clear ownership boundaries and responsibilities for each teammate before spawning
  6. 6.Spawn teammates using the Agent tool with complete context in initial prompts, as they start with no prior conversation history

Use cases

Good for
  • Deciding whether to spawn 2 or 4 agents for a multi-file feature implementation
  • Choosing a Review Team (3 reviewers) for security and architecture assessment across code changes
  • Assembling a Fullstack Team (1 lead + frontend/backend/test implementers) for end-to-end feature development
  • Building a Security Team (4 reviewers) for comprehensive audit covering OWASP, auth, dependencies, and secrets
  • Composing a Migration Team (1 lead + 2 implementers + 1 reviewer) for large codebase upgrades with parallel work and verification
Who it's for
  • Engineering leads and architects designing multi-agent workflows
  • Developers implementing features that benefit from parallel work streams
  • Code reviewers and security teams conducting comprehensive audits
  • DevOps and CI/CD engineers configuring agent teams in automated environments
  • Teams performing large migrations or systemic refactors

team-composition-patterns FAQ

How many agents should I spawn for my task?

Use the team sizing heuristic: 1–2 for simple tasks (single-dimension review, isolated bugs), 2–3 for moderate complexity (multi-file changes, 2–3 concerns), 3–4 for complex work (cross-cutting concerns, large features), and 4–5 for very complex tasks (full-stack features, systemic issues). Start with the smallest team covering all required dimensions; each additional teammate increases coordination overhead.

What is the difference between general-purpose and specialized agent types?

general-purpose agents have all tools (Read, Write, Edit, Bash) and can implement features. Explore and Plan are read-only (Grep, Glob, Read only) for research and analysis. Specialized agents (team-reviewer, team-debugger, team-implementer, team-lead) have targeted tools plus team coordination capabilities. Never assign implementation tasks to read-only agents.

When should I use a preset team composition versus building a custom team?

Use preset compositions (Review, Debug, Feature, Fullstack, Research, Security, Migration) when your workflow matches the pattern. Build custom teams when you have non-standard requirements. Always ensure every custom team has a coordinator (team-lead or user), matches roles to agent types, avoids duplicate roles, defines clear ownership boundaries, and keeps size to 2–4 agents.

What display mode should I use for my environment?

Use tmux mode for development workflows where you want to monitor multiple agents in separate panes. Use iTerm2 mode on macOS if you prefer iTerm2 tabs. Use in-process mode for CI/CD environments or simple tasks where tmux is unavailable. Configure in ~/.claude/settings.json.

Why are my reviewers flagging the same issues?

Review dimensions are overlapping. Redefine each reviewer's focus area explicitly: one on correctness/logic, one on security, one on performance/scalability. This prevents duplicate findings and wasted tokens.

Full instructions (SKILL.md)

Source of truth, from wshobson/agents.


name: team-composition-patterns description: 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. version: 1.0.2

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 — Either designate a team-lead or have the user coordinate directly
  2. Match roles to agent types — Use specialized agents (reviewer, debugger, implementer) when available
  3. Avoid duplicate roles — Two agents doing the same thing wastes resources
  4. Define boundaries upfront — Each teammate needs clear ownership of files or responsibilities
  5. Keep it small — 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 — they need all relevant information in their initial prompt.

Related Skills

  • parallel-feature-development — Decompose work streams and assign file ownership once the team is composed
  • team-communication-protocols — Establish messaging norms and shutdown procedures for the assembled team