claude-teams

Claude Teams

Coordinate multiple Claude Code agents working together on shared tasks.

When forming a team

Invoke /core:agent-loop for the 4-phase / 6-tier execution model. Invoke /claude-code:claude-agents for agent file format, tool allowlists, and model selection. Invoke /core:anti-fabrication always — every claim about a tool, file, or test result requires tool execution.

Require each teammate to quote one sentence from each loaded skill in its first message as proof of loading. Do not proceed with the teammate's work until proof is received.

Glob patterns like /core:* do not expand in Agent prompts. List skill names explicitly.

When to Use

Activate when:

• Setting up or configuring Agent Teams (experimental)
• Creating custom subagents for task delegation
• Building multi-agent workflows with the Claude Agent SDK
• Designing coordination patterns for parallel agent work
• Troubleshooting agent communication or task assignment

Approaches

Three approaches exist for multi-agent coordination, each with different trade-offs:

Approach	Communication	Coordination	Best For
Agent Teams	Peer-to-peer messaging + shared task list	Team lead + self-coordination	Collaborative work requiring discussion
Subagents	Report back to parent only	Parent manages all	Focused delegated tasks
Agent SDK	Programmatic message streaming	Developer-controlled	CI/CD, automation, custom apps

Agent Teams (Experimental)

First-party multi-agent coordination. A team lead spawns teammates that work independently with peer-to-peer messaging and a shared task list.

Enable with: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1

For setup, configuration, and usage details, see references/agent-teams.md.

Subagents (Task Tool)

Lightweight delegation within a single session. Subagents run in their own context window, complete a task, and return results to the parent.

For subagent types, custom agents, and isolation patterns, see references/subagents.md.

Agent SDK

Programmatic multi-agent orchestration in Python and TypeScript using the same tools that power Claude Code.

For SDK setup, agent definitions, and session management, see references/agent-sdk.md.

Multi-Agent Patterns

Proven patterns for file ownership, task decomposition, scaling, and quality gates.

For architecture guidance and case studies, see references/patterns.md.

Orchestration primitives

/core:agent-loop defines the decomposition + delegation flow. Four Claude Code primitives compose with it for long-running or recurring work:

Primitive	Use when
/loop <prompt>	You want a self-pacing tick: monitor agents, poll the tracker, advance the queue. Auto-paces via ScheduleWakeup.
Routines	Cron-style scheduled remote agents. Use for daily/weekly autonomous runs.
Channels	Event-driven (webhook/integration) entry points. Use when an external system kicks the loop.
Workflows	Fan-out exceeds one turn, the orchestration itself must be repeatable, or results need independent verification passes — see /claude-code:claude-workflows.

Workflows require explicit opt-in and run in the background; /core:agent-loop "Optional: workflow execution substrate" defines how the five-tier pipeline maps onto them.

/loop example — shepherd a running epic

After dispatching a team for an epic, the operator session runs:

/loop /shepherd

where /shepherd is a project-defined command (not shipped with this plugin — define it in your project's .claude/commands/) that, each tick:

1. Reads bees/tracker state for the epic's issues
2. Promotes ready issues to in_progress
3. Notifies the operator if any agent transitioned to a review or needs_help state
4. Halts and pings via PushNotification when the cohort is complete

The /loop harness auto-paces via ScheduleWakeup (default 270s — stays inside the prompt-cache TTL). The operator session is hands-off until the loop fires a notification.

This is the recommended composition for long-running multi-agent work: /core:agent-loop does the per-spawn discipline; /loop does the queue advancement.