swarm · diff

git:20261016.71f575d to git:20261016.933be83

3 added, 3 removed. Audit A to A.

---

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

---

# Swarm

## 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.

- 4. Pick the worker model from the `swarm workers` line in `~/.cursor/rules/pstack-models.mdc`. 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. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill.

+ 4. Pick the worker model from the `swarm workers` role in `${CLAUDE_SKILL_DIR}/../poteto-mode/references/models.md`. 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.

+ Spawn all N workers with the Agent tool in one message with `subagent_type: "general-purpose"`, `run_in_background: true`, the configured model, and `isolation: "worktree"` for any worker that checks out a branch, builds, runs the app, or writes. Workers that share the parent's checkout race each other. Use `isolation: "remote"` only when the worker must outlive this session.

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

+ When a worker must start from a non-default pushed branch, its brief names the branch and SHA to check out first.

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.

## Phase D: Report

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