AGENT SKILL

team-composition-patterns

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 the teammate display mode (in-process, auto, tmux, iterm2), or when building a custom team composition for a non-standard workflow such as a migration or security audit.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 0
Forks
0

01 前言 Front Matter

name
team-composition-patterns
version
1.0.2
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 the teammate display mode (in-process, auto, tmux, iterm2), or when building a custom team composition for a non-standard workflow such as a migration or security audit.
last_verified
1793059200000

02 资源文件 2

03 SKILL.md 正文

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 the teammate display mode (in-process, auto, tmux, iterm2)
  • 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

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: 2 implementers; the session is the lead
  • Agents: 2x team-implementer
  • Use when: Feature can be decomposed into parallel work streams

Fullstack Team

  • Size: 3 implementers; the session is the lead
  • Agents: 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: 3 (2 implementers + 1 reviewer); the session is the lead and writes the migration plan
  • Agents: 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 Type Tools Available Use For
general-purpose All tools (Read, Write, Edit, Bash, etc.) Implementation, debugging, any task requiring file changes
Explore Read-only tools (Read, Grep, Glob) Research, code exploration, analysis
Plan Read-only tools Architecture planning, task decomposition
agent-teams:team-reviewer Read/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessage Code review with structured findings
agent-teams:team-debugger Read/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessage Hypothesis-driven investigation
agent-teams:team-implementer Read/Write/Edit/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessage Building features within file ownership boundaries
agent-teams:team-lead Read/search/Bash, Agent, Task tools, SendMessage The main session's role (claude --agent agent-teams:team-lead); never spawned as a teammate

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

Display Mode Configuration

Set teammateMode in ~/.claude/settings.json, or pass claude --teammate-mode <mode> for one session:

{
  "teammateMode": "auto"
}
Mode Behavior Needs
"in-process" All teammates in your terminal; pick one in the agent panel (default) Any terminal
"auto" Split panes inside tmux, or in iTerm2 with it2; in-process otherwise Nothing extra
"tmux" Split panes; detects tmux or iTerm2 from the terminal tmux, or iTerm2 with it2
"iterm2" iTerm2 native split panes it2 CLI and iTerm2's Python API

Split panes don't work in VS Code's integrated terminal, Windows Terminal or Ghostty. Teammates never spawn in non-interactive mode (claude -p), whatever the mode.

Custom Team Guidelines

When building custom teams:

  1. The session is the coordinator — Teammates can't spawn teammates, so the session that spawns them leads. Start it with claude --agent agent-teams:team-lead to give it the lead procedure
  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.

Split panes are not showing. Check which tmux, or for iTerm2 that the it2 CLI is installed and the Python API is enabled. Under "auto", split panes need you to already be inside tmux. in-process works in any terminal.

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.

The 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

04 同仓库更多 Skills