agent-teams

## Table of Contents - [Overview](#overview) - [When to Use](#when-to-use) - [Prerequisites](#prerequisites) - [Protocol Architecture](#protocol-architecture) - [Quick Start](#quick-start) - [Coordination Workflow](#coordination-workflow) - [Module Reference](#module-reference) - [Integration with Conjure](#integration-with-conjure) - [Troubleshooting](#troubleshooting) - [Exit Criteria](#exit-criteria) # Agent Teams Coordination ## Overview Claude Code Agent Teams enables multiple Claude CLI processes to collaborate on shared work through a filesystem-based coordination protocol. Each teammate runs as an independent `claude` process in a tmux pane, communicating via JSON files guarded by `fcntl` locks. No database, no daemon, no network layer. This skill provides the patterns for orchestrating agent teams effectively. ## When To Use - Parallel implementation across multiple files or modules - Multi-agent code review (one agent reviews, another implements fixes) - Large refactoring requiring coordinated changes across subsystems - Tasks with natural parallelism that benefit from concurrent agents ## When NOT To Use - Single-file changes or small tasks (overhead exceeds benefit) - Tasks requiring tight sequential reasoning (agents coordinate loosely) - When `claude` CLI is not available or tmux is not installed ## Prerequisites ```bash # Verify Claude Code CLI claude --version # Verify tmux (required for split-pane mode) tmux -V # Enable experimental feature (set...