MCPInstall

agent-teams-guide

by hexbeeProductivity & Automation

Guide for orchestrating and controlling Claude Code agent teams. Use when working with or managing multi-agent team coordination in Claude Code, including: (1) Creating and starting agent teams, (2) Controlling teammates (display modes, task assignment, delegation), (3) Best practices for parallel work, (4) Troubleshooting team issues. Covers concepts like team lead, teammates, shared task lists, and inter-agent messaging.

Installs
39
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/hexbee/hello-skills --skill agent-teams-guide
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads agent-teams-guide automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Agent Teams Guide

Quick Reference

CommandDescription
Create an agent team...Spawn teammates for parallel work
Clean up the teamShut down all teammates gracefully
Delegate modePress Shift+Tab after starting team
Shift+Up/DownSelect teammate in in-process mode

Enabling Agent Teams

Agent teams are experimental. Enable via environment variable:

{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

Or set the environment variable in your shell before running Claude Code.

Creating a Team

Start a team by describing parallel work that would benefit from multiple perspectives:

Create an agent team to explore this from different angles: one
teammate on UX, one on technical architecture, one playing devil's advocate.

Claude creates:

  • A team lead (your main session)
  • Teammates (separate Claude Code instances)
  • A shared task list for coordination

Display Modes

In-Process Mode (Default)

  • All teammates run in your main terminal
  • Shift+Up/Down to select a teammate
  • Type to message them directly
  • Works in any terminal

Split-Pane Mode

  • Each teammate gets its own pane
  • Requires tmux or iTerm2
  • Set teammateMode in settings.json:
{ "teammateMode": "in-process" }
  • Override per session: claude --teammate-mode in-process

Controlling Teammates

Task Assignment

  • Lead assigns explicitly: tell the lead which task goes to which teammate
  • Self-claim: teammates pick unassigned, unblocked tasks automatically

Direct Communication

  • In-process: Select teammate, type message, press Enter to view, Escape to interrupt
  • Split-pane: Click into pane to interact directly

Delegate Mode

Prevents the lead from implementing tasks itself, keeping it focused on coordination:

  1. Start a team first
  2. Press Shift+Tab to cycle into delegate mode

Require Plan Approval

For complex tasks:

Spawn an architect teammate to refactor the authentication module.
Require plan approval before they make any changes.

Best Practices

Give Teammates Enough Context

Teammates don't inherit lead's conversation history. Include details in spawn prompt:

Spawn a security reviewer teammate with the prompt: "Review the authentication
module at src/auth/ for security vulnerabilities. Focus on token handling,
session management, and input validation..."

Size Tasks Appropriately

  • Too small: coordination overhead exceeds benefit
  • Too large: teammates work too long without check-ins
  • Just right: self-contained units (function, test file, review)

Avoid File Conflicts

Break work so each teammate owns different files. Two teammates editing same file causes overwrites.

Monitor and Steer

Check progress, redirect approaches, synthesize findings. Don't leave teams unattended too long.

Cleanup

When finished:

Clean up the team

The lead removes shared team resources. Always use the lead for cleanup, not teammates.

Troubleshooting

IssueSolution
Teammates not visiblePress Shift+Down to cycle; ensure task warrants a team
Too many permission promptsPre-approve operations in permission settings
Teammates stopping on errorsCheck output, give additional instructions, or spawn replacement
Lead shuts down earlyTell lead to keep going and wait for teammates
Orphaned tmux sessionstmux ls then tmux kill-session -t <name>

When to Use Agent Teams

Best for:

  • Research and review (multiple perspectives simultaneously)
  • New modules or features (independent pieces)
  • Debugging with competing hypotheses (parallel investigation)
  • Cross-layer coordination (frontend, backend, tests)

Not ideal for:

  • Sequential tasks
  • Same-file edits
  • Work with many dependencies

Common Patterns

Parallel Code Review

Create an agent team to review PR #142. Spawn three reviewers:
- One focused on security implications
- One checking performance impact
- One validating test coverage
Have them each review and report findings.

Investigate with Competing Hypotheses

Users report the app exits after one message instead of staying connected.
Spawn 5 agent teammates to investigate different hypotheses. Have them talk
to each other to try to disprove each other's theories.

Limitations

  • No session resumption with in-process teammates
  • Task status can lag behind actual completion
  • Shutdown can be slow (teammates finish current request first)
  • One team per session
  • No nested teams (teammates can't spawn their own)
  • Lead is fixed for team lifetime
  • Split panes require tmux or iTerm2 (not VS Code terminal, Windows Terminal, Ghostty)

FAQ

What does the agent-teams-guide skill do?

Guide for orchestrating and controlling Claude Code agent teams. Use when working with or managing multi-agent team coordination in Claude Code, including: (1) Creating and starting agent teams, (2) Controlling teammates (display modes, task assignment, delegation), (3) Best practices for parallel work, (4) Troubleshooting team issues. Covers concepts like team lead, teammates, shared task lists, and inter-agent messaging.

How do I install agent-teams-guide?

Run npx skills add https://github.com/hexbee/hello-skills --skill agent-teams-guide in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/agent-teams-guide/ (personal) or .claude/skills/agent-teams-guide/ (project).

Which AI agents can use agent-teams-guide?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is agent-teams-guide safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains agent-teams-guide?

It is published by hexbee in hexbee/hello-skills. It has 39 recorded installs.

More from hexbee/hello-skills

View all →

deep-productivity

hexbee/hello-skills

Master deep work productivity through the three types of work framework (Building, Maintenance, Recovery). Use when user needs to: (1) Build a sustainable deep work routine with just 1 hour/day, (2) Create vision/anti-vision for life direction, (3) Structure goals using the 10-year → 1-year → 1-month → 1-week hierarchy, (4) Apply project-based learning to bridge skill gaps, (5) Identify lever-moving tasks that actually progress goals, (6) Balance focus work with necessary recovery for creativity.

Productivity & Automation981 installs

mungers-lattice

hexbee/hello-skills

Open the skill to read its SKILL.md instructions.

102 installs

cross-domain-thinking-toolbox

hexbee/hello-skills

Open the skill to read its SKILL.md instructions.

90 installs

hn-top10

hexbee/hello-skills

Open the skill to read its SKILL.md instructions.

84 installs

learning-first-principles

hexbee/hello-skills

A cognitive framework based on learning first principles, providing learning method diagnosis, efficiency assessment, and optimization advice. Use when: (1) Diagnosing if current learning methods align with first principles, (2) Evaluating learning plan efficiency and time investment, (3) Analyzing learning behavior problems and providing improvement suggestions, (4) Determining if learning content is worth the time investment. Core principle chain: Self-learning → Induction → Self-output → Expression restructuring → Logical understanding → Practice.

Education & Science76 installs

instreet-operator

hexbee/hello-skills

Open the skill to read its SKILL.md instructions.

72 installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

Productivity & Automation815.7K installs

lark-base

open.feishu.cn

飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。

Productivity & Automation815K installs

lark-drive

open.feishu.cn

飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。

Productivity & Automation815K installs

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

Productivity & Automation814.8K installs

lark-im

open.feishu.cn

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

Productivity & Automation814.1K installs