agentleFS
mdsmithaustinmdsmithaustin/pstack/skills/swarm/SKILL.md

swarm

Skill9 starsChanged 37 days agoMITView on GitHub

Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

91 other projects use a version of this, 49 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 87 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

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

    line 44

“Common” is measured: kept by at least 6 in 10 of the 87 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Swarm

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

Start

Open a worklist 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 how many run at once.
  4. Pick each worker's role by what it does. Call the Skill tool with pstack-harness for the spawn. Its Spawn a role section resolves the role and builds this CLI's spawn call.
    • A worker that runs something and reports what it saw uses the swarm workers role, default sonnet. Its PASS or ISSUES comes from a command's output or an observed result. Gate, live, regression, and perf lanes, coverage slices, and exploration partitions are this kind.
    • A worker that reads code, a diff, or another artifact and judges it uses the trail reviewer role, default opus. Audit and review lanes are this kind, and so is a worker that both runs something and judges the work. Before you spawn it, find the model that wrote the work, because Spawn a role passes it as --work-model and the resolver picks a different model in the work model's family for this role when the config allows one and trail reviewer step is not off. When that model is unknown, run the role as resolved and say so in the report.
    • For a model race, name each arm's model up front. A named arm overrides both roles.
  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 no persona, in the background, and with the spawn call Spawn a role builds from each worker's step 4 role.

A worker that must start from another pushed branch gets a worktree at that branch's SHA, named in its brief.

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.

For races, call the Skill tool with arena, then follow its required-arm rule. For coverage, a missing required slice makes the report incomplete. Retain useful results and record the gap. A discretionary worker may drop out with a recorded limitation.

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 a result table, issue one-liners, gaps or dropouts, and the race rule when used.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.