Design optimal agent team compositions with sizing

Team composition patterns

by wshobson · MIT license · ★ 39,857 on GitHub · v1.0.2 · updated Sep 21

Team composition patterns cover

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…

---
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

Overview

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

What you get

  • Size3 (1 lead + 2 implementers)
  • Agents1x team-lead + 2x team-implementer
  • Use whenFeature can be decomposed into parallel work streams
Manual install (npx, ZIP)
Claude Codenpx skills add wshobson/agents --skill team-composition-patterns -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/wshobson/agents/tar.gz/4236bb91f839 \ | tar -xz -C ~/.claude/skills --strip-components=4 agents-4236bb91f839/plugins/agent-teams/skills/team-composition-patterns
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/0783c31bf552fb75b0ac/team-composition-patterns.zip" -OutFile "$env:TEMP\team-composition-patterns.zip"; Expand-Archive "$env:TEMP\team-composition-patterns.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md8.0 KB
  • references/2 files · 12.4 KB
Read the files here
wshobson/4236bb93 files
Shared references2SKILL.md reads these from elsewhere in the repo. Not in the ZIP.Get them on GitHub ↗
SKILL.md
Show the full text142 lines

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

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 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 plus Agent Teams coordination tools Team 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"
}
Mode Behavior Best For
"tmux" Each teammate in a tmux pane Development workflows, monitoring multiple agents
"iterm2" Each teammate in an iTerm2 tab macOS users who prefer iTerm2
"in-process" All teammates in same process Simple 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.

1---
2name: team-composition-patterns
3description: 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.
4version: 1.0.2
5---
6 
7# Team Composition Patterns
8 
9Best practices for composing multi-agent teams, selecting team sizes, choosing agent types, and configuring display modes for Claude Code's Agent Teams feature.
10 
11## When to Use This Skill
12 
13- Deciding how many teammates to spawn for a task
14- Choosing between preset team configurations
15- Selecting the right agent type (subagent_type) for each role
16- Configuring teammate display modes (tmux, iTerm2, in-process)
17- Building custom team compositions for non-standard workflows
18 
19## Team Sizing Heuristics
20 
21| Complexity | Team Size | When to Use |
22| ------------ | --------- | ----------------------------------------------------------- |
23| Simple | 1-2 | Single-dimension review, isolated bug, small feature |
24| Moderate | 2-3 | Multi-file changes, 2-3 concerns, medium features |
25| Complex | 3-4 | Cross-cutting concerns, large features, deep debugging |
26| Very Complex | 4-5 | Full-stack features, comprehensive reviews, systemic issues |
27 
28**Rule of thumb**: Start with the smallest team that covers all required dimensions. Adding teammates increases coordination overhead.
29 
30## Preset Team Compositions
31 
32### Review Team
33 
34- **Size**: 3 reviewers
35- **Agents**: 3x `team-reviewer`
36- **Default dimensions**: security, performance, architecture
37- **Use when**: Code changes need multi-dimensional quality assessment
38 
39### Debug Team
40 
41- **Size**: 3 investigators
42- **Agents**: 3x `team-debugger`
43- **Default hypotheses**: 3 competing hypotheses
44- **Use when**: Bug has multiple plausible root causes
45 
46### Feature Team
47 
48- **Size**: 3 (1 lead + 2 implementers)
49- **Agents**: 1x `team-lead` + 2x `team-implementer`
50- **Use when**: Feature can be decomposed into parallel work streams
51 
52### Fullstack Team
53 
54- **Size**: 4 (1 lead + 3 implementers)
55- **Agents**: 1x `team-lead` + 1x frontend `team-implementer` + 1x backend `team-implementer` + 1x test `team-implementer`
56- **Use when**: Feature spans frontend, backend, and test layers
57 
58### Research Team
59 
60- **Size**: 3 researchers
61- **Agents**: 3x `general-purpose`
62- **Default areas**: Each assigned a different research question, module, or topic
63- **Capabilities**: Codebase search (Grep, Glob, Read), web search (WebSearch, WebFetch)
64- **Use when**: Need to understand a codebase, research libraries, compare approaches, or gather information from code and web sources in parallel
65 
66### Security Team
67 
68- **Size**: 4 reviewers
69- **Agents**: 4x `team-reviewer`
70- **Default dimensions**: OWASP/vulnerabilities, auth/access control, dependencies/supply chain, secrets/configuration
71- **Use when**: Comprehensive security audit covering multiple attack surfaces
72 
73### Migration Team
74 
75- **Size**: 4 (1 lead + 2 implementers + 1 reviewer)
76- **Agents**: 1x `team-lead` + 2x `team-implementer` + 1x `team-reviewer`
77- **Use when**: Large codebase migration (framework upgrade, language port, API version bump) requiring parallel work with correctness verification
78 
79## Agent Type Selection
80 
81When spawning teammates with the `Agent` tool, choose `subagent_type` based on what tools the teammate needs:
82 
83| Agent Type | Tools Available | Use For |
84| ------------------------------ | ---------------------------------------------------- | ---------------------------------------------------------- |
85| `general-purpose` | All tools (Read, Write, Edit, Bash, etc.) | Implementation, debugging, any task requiring file changes |
86| `Explore` | Read-only tools (Read, Grep, Glob) | Research, code exploration, analysis |
87| `Plan` | Read-only tools | Architecture planning, task decomposition |
88| `agent-teams:team-reviewer` | Read/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessage | Code review with structured findings |
89| `agent-teams:team-debugger` | Read/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessage | Hypothesis-driven investigation |
90| `agent-teams:team-implementer` | Read/Write/Edit/search/Bash plus TaskList/TaskGet/TaskUpdate/SendMessage | Building features within file ownership boundaries |
91| `agent-teams:team-lead` | Read/search/Bash plus Agent Teams coordination tools | Team orchestration and coordination |
92 
93**Key distinction**: Read-only agents (Explore, Plan) cannot modify files. Never assign implementation tasks to read-only agents.
94 
95## Display Mode Configuration
96 
97Configure in `~/.claude/settings.json`:
98 
99```json
100{
101 "teammateMode": "tmux"
102}
103```
104 
105| Mode | Behavior | Best For |
106| -------------- | ------------------------------ | ------------------------------------------------- |
107| `"tmux"` | Each teammate in a tmux pane | Development workflows, monitoring multiple agents |
108| `"iterm2"` | Each teammate in an iTerm2 tab | macOS users who prefer iTerm2 |
109| `"in-process"` | All teammates in same process | Simple tasks, CI/CD environments |
110 
111## Custom Team Guidelines
112 
113When building custom teams:
114 
1151. **Every team needs a coordinator** — Either designate a `team-lead` or have the user coordinate directly
1162. **Match roles to agent types** — Use specialized agents (reviewer, debugger, implementer) when available
1173. **Avoid duplicate roles** — Two agents doing the same thing wastes resources
1184. **Define boundaries upfront** — Each teammate needs clear ownership of files or responsibilities
1195. **Keep it small** — 2-4 teammates is the sweet spot; 5+ requires significant coordination overhead
120 
121## Troubleshooting
122 
123**A teammate was spawned as `Explore` but needs to write files.**
124`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.
125 
126**The team is growing too large and coordination is slowing everything down.**
127Each 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.
128 
129**tmux mode is not showing panes.**
130Ensure 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.
131 
132**Two reviewers are flagging the same issues.**
133The 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.
134 
135**A `team-lead` is spawning teammates but they are not receiving tasks.**
136Verify 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.
137 
138## Related Skills
139 
140- [parallel-feature-development](../parallel-feature-development/SKILL.md) — Decompose work streams and assign file ownership once the team is composed
141- [team-communication-protocols](../team-communication-protocols/SKILL.md) — Establish messaging norms and shutdown procedures for the assembled team
142 
View all files on GitHub →

Details

Version
1.0.2
Updated
Sep 21, 2026
License
MIT
Stars on the repo
★ 39,857
Checked
Source
wshobson/agents ↗
Creator
wshobson · 179 listings
View creator

Similar skills

See all →
SkillTests in real browsers via Chrome DevTools MCPBrowser testing with devtoolsaddyosmani/agent-skills · by addyosmaniTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.★ 98.7k GitHub starsMCPThis MCP server attempts to exercise all the featuresEverything MCP Servermodelcontextprotocol/servers · by modelcontextprotocolThis MCP server attempts to exercise all the features of the MCP protocol. It is not intended to be a useful server, but rather a test…★ 90.5k GitHub starsMCPA Model Context Protocol server that provides web contentFetch MCP Servermodelcontextprotocol/servers · by modelcontextprotocolA Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content…★ 90.5k GitHub starsMCPNode.js server implementing Model Context ProtocolFilesystem MCP Servermodelcontextprotocol/servers · by modelcontextprotocolNode.js server implementing Model Context Protocol (MCP) for filesystem operations.★ 90.5k GitHub starsSkillAbout libraries, frameworks, API referencesContext7 MCPupstash/context7 · by upstashThis skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.★ 62.3k GitHub starsSkillUses Chrome DevTools via MCP for efficient debuggingChromeDevTools/chrome-devtools-mcp · by ChromeDevToolsUses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).★ 52.4k GitHub stars

More from wshobson

SkillMaster C/.NET backend development patterns for buildingwshobson/agents · by wshobsonMaster C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications. Covers async/await, dependency injection, Entity Framework Core, Dapper, configuration, caching, and testing with xUnit. Use when developing .NET backends, reviewing C# code, or designing API architectures.★ 39.9k GitHub starsSkillImplement WCAG 2.2 compliant interfaces with mobileAccessibility compliancewshobson/agents · by wshobsonImplement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support. Use when auditing accessibility, implementing ARIA patterns, building for screen readers, or ensuring inclusive user experiences.★ 39.9k GitHub starsSkillMaster Material Design 3 and Jetpack Compose patternsAndroid Mobile Designwshobson/agents · by wshobsonMaster Material Design 3 and Jetpack Compose patterns for building native Android apps. Use when designing Android interfaces, implementing Compose UI, or following Google's Material Design guidelines.★ 39.9k GitHub starsSkillMigrate from AngularJS to Angular using hybrid modeAngular migrationwshobson/agents · by wshobsonMigrate from AngularJS to Angular using hybrid mode, incremental component rewriting, and dependency injection updates. Use when upgrading AngularJS applications, planning framework migrations, or modernizing legacy Angular code.★ 39.9k GitHub starsSkillUnderstand anti-reversing, obfuscationAnti reversing techniqueswshobson/agents · by wshobsonUnderstand anti-reversing, obfuscation, and protection techniques encountered during software analysis. Use this skill when analyzing malware evasion techniques, when implementing anti-debugging protections for CTF challenges, when reverse engineering packed binaries, or when building security research tools that need to detect virtualized environments.★ 39.9k GitHub starsSkillBuild production Apache Airflow DAGs with best practicesApache Airflow DAG Patternswshobson/agents · by wshobsonBuild production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.★ 39.9k GitHub stars