---
name: swarm
description: "Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration."
disable-model-invocation: true
---
## OpenAI runtime contract

Read [the adapter contract](../../references/runtime-contract.md) before this workflow. It maps provider selection, agent calls, loops, persistent state, history, verification, and authorization. That contract supersedes Cursor-specific execution syntax and unverified model fallbacks below; the engineering steps remain required. Use native tools in the current host by default. Cloud uses its available OpenAI models. No remote laptop connection, server URL or MCP setup is permitted. Optional local CLI adapters require explicit environment-local selection. Do not claim cross-provider diversity for OpenAI-only review.


# Swarm

Fan out N parallel cloud workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.

## Start

Open a todolist with one entry per phase before launching anything.

1. Frame
2. Fan out
3. Aggregate
4. Report

## Phase A: Frame

1. State the done predicate and the artifact or report the swarm must return.
2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare `first pass`, `rank all`, or `best-of` before spawning.
3. Set N from the user or derive it from the shape. N is total workers, not the cloud concurrency limit.
4. Pick the worker model from the `swarm workers` line in `the persistent pstack runtime configuration (pstack_config)`. If the rule or that line is missing, use `grok-4.7-xhigh-fast`. For `auto` or `inherit-parent`, omit `model` so the workers run on the parent model. If the Task tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. For a model race, name each arm's model up front.
5. Give each worker its own writable output when it writes. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method (sample count, what one sample is, order). The worker records both in its result.

## Phase B: Fan out

Spawn all N workers in one message with `subagent_type: generalPurpose`, `environment: "cloud"`, `run_in_background: true`, and the step 4 model, left unset for `auto` or `inherit-parent`. Use `environment: "local"` only when the worker needs access to something on the user's computer.

When a worker must start from a non-default pushed branch, pass `cloud_base_branch`.

Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use `PASS`, `ISSUES`, or `BLOCKED` with evidence. A worker that can prove a defect reports `ISSUES` and lists every issue it can prove, not only the first.

If a worker drops out, proceed with N-1 and note it.

## Phase C: Aggregate

Read the terminal results. Drop a result that does not record the SHAs and method its brief names, and respawn that worker once. After a second miss, record a gap. A gap does not count as a pass. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.

Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.

## Phase D: Report

Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.