skilld
All skills
wshobson avatar

/team-composition-patterns

@08ded5e
by Seth Hobsonwshobson/agents40k stars
4,281

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.

Ask your Agent

Use this Skill: https://skilld.dev/gh/wshobson/agents/team-composition-patterns

This session only. Nothing lands on disk.

referencesagent-type-selection.md

≈887 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Agent Type Selection Guide

Decision matrix for choosing the right subagent_type when spawning teammates.

Decision Matrix

Does the teammate need a specialized Agent Teams role?
├── YES → Which role?
│         ├── Team coordination → agent-teams:team-lead
│         ├── Feature building → agent-teams:team-implementer
│         ├── Code review → agent-teams:team-reviewer
│         └── Bug investigation → agent-teams:team-debugger
└── NO → Does it need to modify files?
          ├── YES → general-purpose
          └── NO → Does it need deep codebase exploration?
                    ├── YES → Explore
                    └── NO → Plan (for architecture/design tasks)

Agent Type Comparison

Agent Type Can Read Can Write Can Edit Can Bash Team Tools Specialized
general-purpose Yes Yes Yes Yes No No
Explore Yes No No No No Search/explore
Plan Yes No No No No Architecture
agent-teams:team-lead Yes No No Yes Yes Team orchestration
agent-teams:team-reviewer Yes No No Yes Yes Code review
agent-teams:team-debugger Yes No No Yes Yes Bug investigation
agent-teams:team-implementer Yes Yes Yes Yes Yes Feature building

Common Mistakes

Mistake Why It Fails Correct Choice
Using Explore for implementation Cannot write/edit files general-purpose or team-implementer
Using Plan for coding tasks Cannot write/edit files general-purpose or team-implementer
Using general-purpose for reviews No review structure/checklists team-reviewer
Using team-implementer for research Has tools but wrong focus Explore or Plan

When to Use Each

general-purpose

  • One-off tasks that don't fit specialized roles
  • Tasks requiring unique tool combinations
  • Ad-hoc scripting or automation

Explore

  • Codebase research and analysis
  • Finding files, patterns, or dependencies
  • Understanding architecture before planning

Plan

  • Designing implementation approaches
  • Creating task decompositions
  • Architecture review (read-only)

team-lead

  • Coordinating multiple teammates
  • Decomposing work and managing tasks
  • Synthesizing results from parallel work

team-reviewer

  • Focused code review on a specific dimension
  • Producing structured findings with severity ratings
  • Following dimension-specific checklists

team-debugger

  • Investigating a specific hypothesis about a bug
  • Gathering evidence with file:line citations
  • Reporting confidence levels and causal chains

team-implementer

  • Building code within file ownership boundaries
  • Following interface contracts
  • Coordinating at integration points

Source: SKILL.md on GitHub

Third-party checks

No alerts16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill acts as an educational and operational guide for configuring multi-agent teams. It outlines sizing heuristics, agent roles, preset configurations, and display choices without introducing any executable code, dependencies, or security risks.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer7mo

    3 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 08ded5e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 5 months ago

Capability

version
1.0.2

Topics

  • agent-teams
  • multi-agent
  • team-composition
  • team-sizing
  • agent-types
  • coordination
  • claude-code
  • workflow-design

README badge

README badge for wshobson/agents/team-composition-patterns

What it does

Guides selecting agent team sizes, preset configurations (review, debug, feature, fullstack, research, security, migration), and agent types (general-purpose, Explore, Plan, team-reviewer, team-debugger, team-implementer, team-lead) based on task complexity and required capabilities. Use this skill when deciding how many agents to spawn, choosing between team templates, or matching agent types to their available tools.

Generated from the current SKILL.md.

Frequently asked

What agent types should I use for code review versus implementation?
Use `team-reviewer` for code review (read/search/Bash plus structured task tools), and `team-implementer` for building features (read/write/edit plus task coordination). Never use read-only agents like `Explore` or `Plan` for implementation tasks.
How many agents should I spawn for a feature that spans frontend, backend, and tests?
Use a Fullstack Team: 1x `team-lead` + 1x frontend `team-implementer` + 1x backend `team-implementer` + 1x test `team-implementer`. This composition lets you parallelize work across three implementation layers with a lead coordinating.
What display mode should I use in CI/CD environments?
Use `in-process` mode, configured in `~/.claude/settings.json`. This runs all teammates in the same process without requiring tmux or iTerm2 and works reliably in automated environments.
Can I have two agents working on the same review dimension?
No. Two reviewers with overlapping focus areas waste tokens and produce duplicate findings. Define distinct dimensions for each reviewer, such as security, performance, and architecture.
What tools are available to a `team-lead`?
A `team-lead` has read/search/Bash plus Agent Teams coordination tools for spawning teammates and orchestrating work. They cannot write files directly — implementers handle that.

Generated from the current SKILL.md. These answers refresh after source changes.