Guides
Make multiple coding agents work like a team.
Short answers to the coordination problems that appear once you run more than one agent.
Claim before edit
Stop AI coding agents overwriting each other's files
Running two or three agents on one repo? Have each one claim files before editing, so the second agent learns about the first before it writes anything.
Read guideCross-harness messaging
Let Claude Code and Codex talk to each other
Send direct, replyable messages between Claude Code, Codex, Cursor and other harnesses, without copying context between windows yourself.
Read guideSurvive compaction
Keep agent state after context compaction
When a coordinator or long-running agent compacts its context, task status and decisions shouldn't go with it. Keep them in the workspace, not the chat.
Read guideMany lanes
Run many parallel coding agents without losing track
Four agents plus subagents, or nine sessions at once: keep every lane's owner, scope and status visible from one place.
Read guideShared environment
Worktrees don't isolate your database or ports
Git worktrees keep agents' files apart, but they still share the dev database, migrations, ports and other local services. Declare those as shared risks.
Read guideMemory between runs
Persist agent decisions between sessions
Where does an agent's memory live between runs? Keep decisions, assumptions and "done" status attached to the task, where the next session can read them.
Read guideEdit gate
Block an agent from editing a file another agent claimed
Turn claims into a hard stop: a Claude Code PreToolUse hook, a git pre-commit hook or CI can refuse edits to files another active task owns.
Read guideWorktrees
Use git worktrees with parallel AI coding agents
Worktrees give each agent its own checkout and branch. Here is what they solve, what they leave open, and how to keep worktree agents aware of each other.
Read guideSubagents or sessions
Claude Code subagents vs parallel sessions
Subagents work for one session and report back. Parallel sessions work independently. Each needs different coordination.
Read guideClaude Code + Cursor
Use Claude Code and Cursor on the same project
Run Claude Code in the terminal and Cursor in the editor on one repository without each tool undoing the other's work.
Read guideGemini CLI
Run Gemini CLI alongside Claude Code and Codex
Add Gemini CLI to a repo where Claude Code or Codex is already working, with shared claims, messages and task memory across all three.
Read guideInstruction files
AGENTS.md vs CLAUDE.md when you run several agents
Codex reads AGENTS.md, Claude Code reads CLAUDE.md, Cursor reads its rules. Keep standing instructions in one place, and keep live work-state out of all of them.
Read guideSetup
Add an MCP server for multi-agent coordination
One command registers a local coordination MCP server with Claude Code, Codex, Cursor, Gemini CLI and Grok Build in a repository.
Read guideStale claims
Find work an AI coding agent abandoned mid-task
Sessions crash, get closed or hit limits. Spot claims whose agent has gone, see what it recorded, and hand the work to someone else.
Read guideAssignment
Assign tasks to AI coding agents and know they accepted
Give a task to a specific agent and get an explicit accept or decline, instead of assuming a prompt was read.
Read guideOrchestration vs coordination
Do you need an orchestrator for multiple coding agents?
Orchestrators decide what runs. Coordination keeps agents that are already running from conflicting. Most teams with several coding agents need the second first.
Read guideVisibility
See what all your coding agents are doing right now
One view of every agent in the repo: who is present, what each has claimed, live overlaps, stale claims and work ready for review.
Read guideParallel Claude Code
Run multiple Claude Code agents in the same repo
Split work between parallel Claude Code sessions without duplicate edits, hidden assumptions, or agents colliding on the same task.
Read guideAvoid agent collisions
Prevent AI coding agents from conflicting
Stop two coding agents from editing overlapping work or making incompatible decisions before the conflict reaches review.
Read guideCross-tool context
Share context between Claude Code, Codex and Cursor
Give different coding agents the same live understanding of tasks, decisions, blockers, and work already in progress.
Read guideAgent handoffs
Hand off work between AI coding agents
Move an unfinished task from one coding agent to another without losing what was tried, decided, changed, or left unresolved.
Read guideAgents across machines
Coordinate coding agents across machines
Keep local, cloud and remote coding agents aware of the same work even when they run in different terminals or environments.
Read guideMulti-agent review
Review and merge work from multiple AI coding agents
Keep parallel agent changes understandable when several branches or worktrees converge into one codebase.
Read guide