COORD
Multi-agent coordination
One agent is a tool. Ten agents in one repository are a team with no memory of each other. These guides cover the parts that break first: who owns a file, how a task is handed over, where shared state lives and how two agents avoid committing each other's half-finished work.
- COORDHow to Run Claude Code Agent Teams Without Overlapping Repository EditsHow to use Claude Code agent teams without overlapping repository edits by enabling the experimental mode, assigning distinct file sets, and checking task completion.
- COORDHow to Run Concurrent Coding Agents in Git Worktrees Without Merge CollisionsA Git worktree gives each coding agent a separate checkout, while path ownership and atomic shared-file edits reduce—but do not eliminate—merge collisions.
- COORDHow to Design Multi-Agent Systems with Handoffs, Shared State, and VerificationA practical guide to multi agent systems that gives handoffs an ownership contract, shared state an update contract, and verification an end-state check.
- COORDHow to Structure Parent, Worker, and Reviewer Agents in Claude CodeA practical claude code multi agent pattern that keeps coordination in the main conversation, delegates bounded work to separate-context subagents, and reviews changes against explicit criteria.
The first guides in this track are being written and checked against the tools' own documentation.