AGENT SKILL

swarm

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

License 许可
MIT
所属仓库
casualjim/pi-mimir
最近更新
2026-11-10
Stars
★ 16
Forks
9

01 前言 Front Matter

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

03 SKILL.md 正文

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.
  3. Set N from the user or derive it from the shape.
  4. Pick the worker model from your configured swarm-workers models (default inherit-parent) and the thinking level the work needs. 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 parallel subagent call using its tasks array. Use agent: "poteto-agent" unless a workflow names another agent, set role: "swarm workers", and pass the thinking level step 4 picked. Child processes run locally with isolated context, so give each task explicit file pointers and prevent concurrent writes to shared paths.

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

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.

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.

04 同仓库更多 Skills