agentleFS
Sign inStart free
edenbuildsedenbuilds/agentloop/.agents/skills/subagent-swarm/SKILL.md

subagent-swarm

Skill0 starsChanged 4 months agoMITView on GitHub

Spawn and manage a capped subagent swarm for parallel independent work with structured returns. Use only when Overmind/Conductor verdict is surgical swarm — large AND independent tracks.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default max_workers=3, max_depth=2.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Subagent Swarm

Decision rubric (Overmind)

Spawn only if all are true:

  1. Work is large enough that parallelization saves wall time or isolates huge contexts.
  2. Tracks are independent (minimal shared-file / shared-state conflict).
  3. Conductor plan §3 swarm_verdict is surgical and approved.
  4. A single strong sequential pass would be worse — not merely slower by a little.

Otherwise stay sequential (PEV). Craft/polish → quality-compose, never swarm.

Steps

  1. Partition into independent tasks (from Conductor parallelization map).
  2. Cap workers/depth; leaves cannot spawn.
  3. Fresh scoped briefs; least privilege.
  4. Structured returns only (see swarm-captain schema).
  5. Steer/kill on no-progress; cleanup sessions.
  6. Fold returns into .agentloop/plan.md + handoff; drop raw worker chat (context-surgeon).

Default max_workers=3, max_depth=2. Exceeding caps requires explicit user raise.

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.

Check your setup, free