Agent Teams
技能 已验证 活跃Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
To enable teams of AI agents to collaborate effectively on complex coding tasks by providing mechanisms for coordination, knowledge sharing, and persistent learning.
功能
- Coordinate multiple AI sessions as a team
- Shared task lists and mailbox messaging
- File-lock claiming to prevent conflicts
- Persistent memory and knowledge plane via SQLite
- Auto-research loop for knowledge growth
- Detailed patterns for team sizing and task decomposition
使用场景
- Collaborating on large codebases with multiple AI agents
- Ensuring AI agents retain knowledge across sessions
- Building persistent knowledge bases for AI research
- Managing complex development workflows with clear task delegation and review
非目标
- Replacing direct human collaboration
- Managing individual AI agent's internal state beyond shared knowledge
- Providing a generic task management system outside of AI agent workflows
安装
请先添加 Marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflow质量评分
已验证类似扩展
Orchestrate
100Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
Context Mode
100从 GitHub 更新 context-mode 并修复 hooks/settings。 拉取最新代码，构建，安装，更新 npm 全局包，配置 hooks。 触发器：/context-mode:ctx-upgrade
Ce Compound
99Document a recently solved problem to compound your team's knowledge
Swarm Orchestration
100Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
Team Lead Persona
100Lead a team — run standups, coordinate tasks, and communicate.
Ce Brainstorm
100Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.