From ai-devkit
Exchange information with active AI agents (Codex, Claude Code) using ai-devkit commands to list, inspect, and send messages between agents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-devkit:agent-communicationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use `ai-devkit agent ...` to discover and communicate with active agents. If `ai-devkit` is not on PATH, use `npx ai-devkit@latest agent ...`.
Use ai-devkit agent ... to discover and communicate with active agents. If ai-devkit is not on PATH, use npx ai-devkit@latest agent ....
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
list --json returns active agents with fields such as name, type, status, summary, projectPath, and lastActive.name from list --json as --id. Partial matches are supported, but exact names are safer.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.npx claudepluginhub codeaholicguy/ai-devkitManages running AI agents with ai-devkit agent commands. Use to list, inspect, start, assign, group, resume, stop, or delegate work to agents.
Lists all core, expert, and self-evolving agents in Claude Code's Director Mode. Invoke via /agents to see available agents.
Lazy-loads specialized agents on-demand via search_agents and get_agent tools, reducing context window usage by ~95%.