Agent Communication

This lets Claude Code talk to other AI agents running on your machine through the ai-devkit CLI. You can list active agents, peek at their recent context with the tail flag, and send messages back and forth. The wait flag is clever: your agent can actually block until it gets a reply, with configurable timeouts. Useful if you're running multiple specialized agents and want them to coordinate, like having a code agent ask a docs agent for API details or piping command output between them. It's niche but solves a real problem once you're deep enough into multi-agent workflows that they need to actually exchange information beyond just working in parallel.

GitHub stars: 1.3K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add codeaholicguy/ai-devkit --skill agent-communication --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Communication

Use ai-devkit agent ... to discover and communicate with active agents. If ai-devkit is not on PATH, use npx ai-devkit@latest agent ....

Commands

ai-devkit agent list --json
ai-devkit agent detail --id <agent-name> --json --tail 20
ai-devkit agent send --id <agent-name> "<message>"
ai-devkit agent send --id <agent-name> --wait --timeout 120000 --json "<message>"
<command> 2>&1 | ai-devkit agent send --id <agent-name> --stdin

Notes

list --json returns active agents with fields such as name, type, status, summary, projectPath, and lastActive.
Use the name from list --json as --id. Partial matches are supported, but exact names are safer.
Use detail --json --tail <n> to read recent context from an agent before deciding what to send.
send --wait waits for a reply; add --json when the response should be machine-readable.
send --stdin forwards piped command output or larger text.