From wit
Coordinates with other AI agents using Wit CLI before code edits: declares intents, locks symbols, checks conflicts to prevent merge issues in multi-agent workflows.
How this skill is triggered — by the user, by Claude, or both
Slash command
/wit:coordinateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are working in a repository where **Wit** may be used for multi-agent coordination. Other AI agents may be working on this codebase simultaneously. Follow this protocol to prevent merge conflicts.
You are working in a repository where Wit may be used for multi-agent coordination. Other AI agents may be working on this codebase simultaneously. Follow this protocol to prevent merge conflicts.
test -d .wit && echo "wit:active" || echo "wit:inactive"
wit status to see what other agents are doing.wit command exists:
command -v wit >/dev/null 2>&1 && echo "wit:installed" || echo "wit:not-installed"
wit init to start coordination.Declare your intent — announce what you plan to work on:
wit declare --description "Brief description of planned work" --files src/path/to/file.ts
Check the response for conflicts. If hasConflicts is true, read the conflict items — another agent may be working in the same area. Adjust your approach if needed.
Lock specific symbols you plan to modify (functions, classes, types):
wit lock --symbol "src/path/to/file.ts:functionName"
If you get a LOCK_CONFLICT, another agent is actively editing that symbol. Work on a different part of the code instead.
Check coordination state at any time:
wit status
This shows all active intents, locks, and contracts across all agents.
wit release --symbol "src/path/to/file.ts:functionName"
wit commands fail with connection errors, the daemon may not be running. Run wit init to restart it.--json flag on any command gives machine-readable output.wit is not installed (command -v wit fails), skip all coordination silently.npx claudepluginhub amaar-mc/wit --plugin witCoordinates multiple Claude Code sessions as a team with a lead delegating tasks, mailbox messaging, and file-lock claiming. Includes patterns for task decomposition, dependency management, and team sizing.
Provides prompt templates for building AI coding agents: system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination patterns.
Surfaces AI collaboration protocols when users refer to entities by colloquial labels, ask how to structure a Claude workflow, or describe multi-step work without durable URLs.