skills.rest
Jhabbig
JhabbigCOMMUNITY
Explore all skills by this author →
GitHub

team-composition-patterns

Select optimal multi-agent team compositions for review, debug, feature, fullstack, research, security, and migration workflows.

Updated Apr 5, 2026
Search Tags:#code review#tmux#workflow planning#team composition#agent teams#subagent types
One-click install
npx skills add https://github.com/Jhabbig/Habbig --skill team-composition-patterns-jhabbig
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: team-composition-patterns
Source: https://github.com/Jhabbig/Habbig/tree/main/.claude/plugins/wshobson/agent-teams/skills/team-composition-patterns
Command: npx skills add https://github.com/Jhabbig/Habbig --skill team-composition-patterns-jhabbig

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you decide how many agents to spawn, which roles they should take, and how to configure them so parallel work stays efficient instead of becoming noisy or redundant.

Core Features & Use Cases

  • Team sizing heuristics: Choose the smallest team that covers the task, from simple one-off work to complex cross-cutting efforts.
  • Preset team designs: Use review, debug, feature, fullstack, research, security, and migration presets instead of inventing a structure from scratch.
  • Agent type selection: Match each role to the right subagent type so reviewers review, implementers build, and read-only agents stay in research and planning lanes.
  • Display mode guidance: Pick tmux, iTerm2, or in-process setups based on the environment and how you want to observe teammates.
  • Use case: If you need a security audit, this Skill can compose a focused reviewer team with clear dimensions such as vulnerabilities, auth, dependencies, and configuration.

Quick Start

Ask for the smallest effective agent team for your task, and have the Skill recommend the roles, subagent types, and display mode to use.

Frequently Asked Questions about team-composition-patterns

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I determine the right multi-agent team composition for a software development task?▼

To determine multi-agent team composition, select the smallest team that covers the task, then match subagent types to specific roles and choose an appropriate display mode like tmux or iTerm2 to keep parallel work efficient.

What is the best way to size an agent team for parallel coding workflows?▼

The best way to size an agent team is using sizing heuristics that choose the fewest agents needed to cover the workflow, preventing parallel work from becoming noisy or redundant across complex cross-cutting efforts.

How do I configure subagent types for a security audit or code review?▼

To configure subagents for a security audit or code review, use preset team designs that assign read-only agents to research and planning lanes, while dedicated reviewers focus on vulnerabilities, auth, dependencies, and configuration.

Can I use tmux or iTerm2 to observe multiple agents during fullstack development?▼

Yes, you can use tmux, iTerm2, or in-process setups to observe multiple agents during fullstack development. Display mode guidance helps pick the right environment based on how you want to monitor teammates.

When should I avoid spawning multiple agents for a feature workflow?▼

You should avoid spawning multiple agents for a feature workflow when the task is a simple one-off effort, as sizing heuristics recommend using the smallest effective team to prevent redundant and noisy parallel work.

Related Skills

Explore More Software Engineering Skills→
PriyanshKuniyalPriyanshKuniyal

team-composition-patterns

Design custom agent team compositions for Claude Code's Agent Teams feature.

Community
Advanced
hiromimahiromima

tmux × iTerm2 Integration

Automate tmux session orchestration with iTerm2 dynamic profiles for agent panes.

Community
Advanced
smith-hornsmith-horn
75

flow-nexus-swarm

Deploy and manage cloud-based AI agent swarms with Flow Nexus.

Official
Advanced
PoseidoncodePoseidoncode

dispatching-parallel-agents

Dispatch independent tasks to parallel agents for concurrent investigation.

Community
Intermediate