mcpbeat Sign in

Swarm Agent Skill

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

655 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
255
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/michael-denyer/pstack-claude --skill swarm

What it tells the agent to use

found in the instruction text
Task spawns other agents

The instruction itself

7 sections, as written by the author

Swarm

On Codex, read the platform mapping, including its per-skill notes, before following this skill.

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 todolist with one entry per phase before launching anything.

  • Frame
  • Fan out
  • Aggregate
  • Report

Phase A: Frame

  • State the done predicate and the artifact or report the swarm must return.
  • 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.
  • Set N from the user or derive it from the shape. N is total workers, not the number that run at once.
  • Pick the worker model from swarm workers in ~/.claude/pstack-models.md when present. Otherwise use the default in Models. For a model race, name each arm's model up front.
  • Give each worker its own writable output when it writes.

Phase B: Fan out

Spawn all N workers in one message with subagent_type: "general-purpose", run_in_background: true, and the configured model. Claude Code subagents all run on this machine, so isolation comes from the worktree or output directory assigned in Phase A, not from a remote environment.

When a worker must start from a non-default branch, check that branch out in the worker's own worktree and name the worktree path 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.

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

Phase C: Aggregate

Read the terminal results. 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.

Models

Role defaults, stamped from plugins/pstack/models.json (edit there, rerun tools/generate.mjs). A matching role line in ~/.claude/pstack-models.md overrides each at runtime; see /setup-pstack.

  • swarm workers: claude-opus-5

How to use it

Copy the folder

Take michael-denyer/swarm from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.