agent-teams
Use when the user is NEW to Claude Code agent teams or asks high-level questions about what they are, when to use them, or how they compare to subagents. Triggers: "how do agent teams work", "what are agent teams", "agent teams vs subagents", "should I use a team for this", "are agent teams enabled". Do NOT trigger for choosing a specific team blueprint (route to `team-blueprints`) or managing an active team (route to `team-coordination`). This skill is the onboarding / discovery entry point only.
What this skill does
# Agent Teams — Overview
Agent teams coordinate multiple Claude Code sessions on complex tasks. One session is the **team lead** (coordinates work); **teammates** work independently in their own context windows and message each other directly.
## When agent teams add value
| Use Case | Why Teams Excel |
|----------|----------------|
| Research & Discovery | Multiple teammates investigate different aspects simultaneously |
| Feature Development | Each teammate owns a separate module — no file conflicts |
| Code Review & QA | Reviewers apply different lenses (security, performance, tests) in parallel |
| Debugging | Teammates test competing hypotheses and challenge each other |
| Cross-Layer Coordination | Frontend, backend, and tests each owned by a different teammate |
## Agent Teams vs Subagents
| Aspect | Subagents | Agent Teams |
|--------|-----------|-------------|
| **Context** | Own window; results return to caller | Own window; fully independent |
| **Communication** | Report back to main agent only | Teammates message each other directly |
| **Coordination** | Main agent manages all work | Shared task list with self-coordination |
| **Best for** | Focused tasks where only the result matters | Complex work requiring discussion and collaboration |
| **Token cost** | Lower (results summarized back) | Higher (each teammate is a separate instance) |
**Rule of thumb:** Use subagents for quick focused workers. Use agent teams when teammates need to share findings, challenge each other, and coordinate independently.
## When NOT to use a team
Teams add ~40 coordination tool calls of overhead per team. Skip teams when:
- Fewer than 3 genuinely parallel workstreams
- A single agent can hold all necessary context
- The task is primarily sequential
- Total expected work is under ~30 minutes
Sizing guidelines and per-blueprint compositions are documented in `team-blueprints` (skill) and `${CLAUDE_PLUGIN_ROOT}/shared/efficiency-guidelines.md`.
## Prerequisites
Agent teams are experimental and must be enabled:
```json
// settings.json
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
```
## Quick Start
```
/spawn-build add user authentication with OAuth and JWT
/spawn-think evaluate React state management libraries
/spawn-create brainstorm API authentication approaches
```
Or describe the task in natural language and Claude will propose a team.
## Where to go next
| You want to... | Skill / Command |
|---|---|
| See pre-designed team configurations for 8 development phases | `team-blueprints` skill |
| Apply deep behavioral profiles (Auditor, Architect, Refiner, etc.) to teammates | `team-personas` skill |
| Manage an active team (tasks, communication, shutdown) | `team-coordination` skill |
| Spawn a build team (feature or debug) | `/spawn-build` command |
| Spawn a think team (research, planning, or review) | `/spawn-think` command |
| Spawn a create team (design, brainstorm, or productivity) | `/spawn-create` command |
| Wrap related spawns in a multi-stage project pipeline | `/project` command |
| Design a custom team that doesn't match a blueprint | `team-architect` agent |
## Reference
For complete API documentation, tool descriptions, architecture, and the full pattern catalog, see [references/agent-teams-reference.md](references/agent-teams-reference.md).
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.