SuperAPI AI Directory

swarm

Agents & models

View repository

Updated 11-01 16:53

About this skill

Swarm

A skill named in bold or in backticks, or run as /<name>, is the file ../<name>/SKILL.md beside this skill's directory, and a principle named without its prefix is ../principle-<name>/SKILL.md. Read the file and follow it. Most pstack skills are user-only, so your skill tool cannot load them. Every subagent is a Rex worker pane: spawn, wait and close it per ../rex-subagents/SKILL.md, with the defaults in the Subagents section of ../poteto-mode/SKILL.md.

Start

Open a task list (your harness's task tool, or a checklist file at ~/.local/state/pstack/checklists/<repo>-<branch>.md when it has none) 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. Pick the worker model from the swarm workers line in ~/.config/pstack/pstack-models.md, and pass the entry to subagent spawn --entry as written. For auto or inherit-parent, or when the file or that line is missing, run the workers on your own harness and its default model. With no file, say so and suggest /setup-pstack. If a worker's model is rejected, run that worker on its harness's default model and say so. 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. 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 turn, one subagent spawn each, named for the slice or race arm, with the step 3 entry. Workers share your checkout, so parallel writers there own disjoint files and run no git commands. A worker that writes, or must start from another commit or branch, gets its own --worktree <branch> --base <commit or branch>. Commit first, because uncommitted edits do not reach a new worktree. One writer per worktree or 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.

End the turn after spawning. Each worker's wake-up line starts your next turn. 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 a result table, issue one-liners, gaps or dropouts, and the race rule when used.