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
- 最近更新
- 2026-10-13
- Stars
- ★ 63
- Forks
- 3
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
Fan out N parallel cloud 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, orbest-ofbefore spawning. - Set N from the user or derive it from the shape. N is total workers, not the cloud concurrency limit.
- Pick the worker model from
swarm workersin the pstack settings file when present (~/.cursor/rules/pstack-models.mdcin Cursor,~/.agents/pstack-models.mdin other harnesses). Otherwise usegrok-4.6-fast-xhigh. 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: generalPurpose, environment: "cloud", run_in_background: true, and the configured model. Use environment: "local" only when the worker needs access to something on the user's computer.
When a worker must start from a non-default pushed branch, pass cloud_base_branch.
Other harnesses. These parameters belong to Cursor's Task tool, and environment: "cloud" runs a Cursor cloud agent. In another harness, use its subagent tool: Agent in Claude Code (subagent_type: general-purpose), task in OpenCode (subagent_type: general), spawn_agent in Codex. Workers run locally there, so give each one its own worktree or output path. Keep the brief and the model. Drop parameters your tool doesn't have. If your harness has no subagent tool, as in Pi without an extension, run the workers yourself, one after another.
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.
04 同仓库更多 Skills
pi-tidy-bots-cli
Drive the pi-tidy-bots fleet runtime from an agent — init, daemonized start, status, stop, hot bot onboarding, and the HTTP+WS machine API (messages, transcripts, compaction, question cards) — all non-interactive with checked exit codes and --json shapes.
qa-loop
Run a human-gated QA and repair loop for pi-tidy-tools.
pi-tidy-tools-ethos
Narrative guardrails for @mobrienv/pi-tidy-tools. Use when designing, implementing, reviewing, or documenting non-release changes to that package.
npm-release
Releases one @mobrienv/pi-tidy-* workspace through GitHub and npm Trusted Publishing. Use when asked to prepare changelog entries, cut, publish, or monitor a patch, minor, major, or explicit-version release.
build-loop
Build and independently verify one ready implementation ticket through a human-gated repair loop.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.