CodeGrid is a native macOS canvas where multiple coding agents (Claude, Codex, Gemini, Cursor, Grok, shells) run side by side in panes and collaborate via a local agent bus — no tmux, no cloud, no account, no stored API keys. Install this skill when an agent should know how to operate inside a CodeGrid pane, drive the workspace from outside (control socket or codegrid:// deep links), spawn or message sibling agents, or coordinate multi-agent work (delegate, review, pipeline, parallel fan-out, monitor, debate). The differentiator: multiple coding agents collaborating on one canvas, addressable by stable session_id, with a read → message → read protocol built for orchestration.
How to collaborate with other AI agents running in CodeGrid using the codegrid-agent-bus MCP tools (list_agents, read_pane, message_agent). Use this skill whenever the user asks you to delegate to, consult, coordinate with, review with, hand work to, or get a second opinion from another agent ("ask Codex to…", "have Gemini review…", "get the other agent to…", "split this up between the agents"). Covers the read→message→read protocol, identifying agents, orchestration patterns (delegate, review, pipeline, parallel fan-out, monitor, debate), etiquette, scope/safety, loop prevention, failure recovery, and worked end-to-end examples.
How an AI coding agent should operate inside CodeGrid — the macOS canvas that runs Claude, Codex, Gemini, Cursor, Grok, and shells side by side and lets them collaborate. Use this skill whenever you are running in a CodeGrid pane, or a user asks you to spawn/list/control agents, open a project, drive the workspace, or coordinate work across panes. Covers the local control socket (agent_list / agent_read / agent_send, open_folder, new_session, new_workspace), the codegrid:// deep-link scheme, the canvas/pane/workspace model, and the operating playbook.