Multi-agent skill
Agent Communication Skill
Exchange information with active Codex, Claude Code, and other AI agents.
On this page
Install command
AI DevKit installs its built-in skills as one curated set. Run this once to install agent-communication with the rest of the built-in workflow skills.
npx ai-devkit@latest skill add --built-inWhat it does
Use agent-communication when you need one agent to find another active agent, read its recent context, or send it follow-up instructions. It supports multi-agent workflows where work is split across terminals or tools.
When to use it
- Find active coding agents and inspect their recent context
- Send instructions or handoff notes to another agent
- Coordinate parallel AI coding sessions without copying context by hand
Supported agents
- Claude Code
- Codex
- opencode
The SKILL.md file
This is what your agent reads when the skill runs. View it on GitHub (opens in a new tab)
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 --jsonreturns active agents with fields such asname,type,status,summary,projectPath, andlastActive.- Use the
namefromlist --jsonas--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 --waitwaits for a reply; add--jsonwhen the response should be machine-readable.send --stdinforwards piped command output or larger text.