메뉴
Guide for coordinating multiple Claude Code agents as teams. Use when setting up agent teams, configuring subagents, orchestrating multi-agent workflows, or building programmatic agent systems with the Claude Agent SDK.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Identify and refactor Rust anti-patterns and clippy anti-idioms. Use when reviewing Rust code for smells, hunting anti-patterns to fix or remove, or refactoring code that clones to satisfy the borrow checker, takes &String/&Vec parameters, unwraps on fallible paths, or returns sentinel values instead of Option/Result.
Guide for async and concurrent Rust programming. Use when writing async functions, using tokio, spawning threads, working with channels, or sharing state with Arc/Mutex.
Guide for building Rust command-line applications. Use when parsing CLI arguments with clap, adding progress bars or verbosity flags, testing a CLI binary as a subprocess, choosing process exit codes, or reporting errors to end users with anyhow context.
Guide for Rust error handling. Use when working with Result, Option, the ? operator, implementing custom error types, or composing errors with thiserror and anyhow.
Guide for Rust ownership, borrowing, and lifetimes. Use when working with ownership rules, move semantics, borrowing, slices, or lifetime annotations.
Guide for Rust programming language. Use when writing Rust code, setting up Rust projects, or needing an overview of Rust development workflows.
| name | claude-teams |
| description | Guide for coordinating multiple Claude Code agents as teams. Use when setting up agent teams, configuring subagents, orchestrating multi-agent workflows, or building programmatic agent systems with the Claude Agent SDK. |
| license | MIT |
Coordinate multiple Claude Code agents working together on shared tasks.
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.
Activate when:
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 |
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.
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.
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.
Proven patterns for file ownership, task decomposition, scaling, and quality gates.
For architecture guidance and case studies, see references/patterns.md.
/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.
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:
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.