Agent swarm (mixed Antigravity + Codex, parallel)
agent_swarmExecute tasks concurrently on both Antigravity and Codex backends, with each worker reporting its own output.
Instructions
Run SEVERAL tasks IN PARALLEL across BOTH backends in a single swarm.
Each task is its own worker and names the backend to run on, so one swarm can
mix Antigravity (Gemini) and Codex workers — they run truly concurrently
(capped at max_concurrency) and every answer comes back in one labelled
block. A worker that fails is reported in place; the others still return.
SECURITY: this launches N unsandboxed agents at once — N times the prompt-injection surface of a single call (see the module SECURITY note). Only use it with trusted prompts on trusted content.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tasks | Yes | One object per parallel worker: - backend: "antigravity" (alias "agy"/"gemini") or "codex" (required) - prompt: the question or instruction (required) - workspace: working dir for that worker (default: server cwd) - sandbox: Codex only — "read-only" (default), "workspace-write", or "danger-full-access". Ignored for Antigravity. - model: Codex only — model override (`-m`). Ignored for Antigravity. | |
| watch | No | If true, open the live "Agent Swarm" dashboard window (one row per worker, with a backend badge; click a row for its full step log). | |
| timeout_s | No | Per-worker timeout in seconds. Default 180. | |
| max_concurrency | No | Max workers running at once (default 4). Higher = faster but more quota/rate-limit pressure and more agents at once. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |