Fan out N independent workers, collect their results, and return one report for coverage, races, gauntlets, or exploration.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Swarm
Fan out N independent 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.
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 the cloud concurrency limit.
4. Inherit the parent model unless the host supports model selection and the race explicitly compares models. Name each model-race arm up front.
5. Give each worker its own writable output when it writes. Use a worktree, branch, or `/tmp/swarm-<slug>/worker-<n>/`.
## Phase B: Fan out
Use the host's native subagent tool to start all N workers concurrently. Give each worker the minimum file and tool access its slice needs. If subagents are unavailable or forbidden, run each slice inline and preserve the same result schema.
…
The line at the top of this page pins the label git:20260827.04830a9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_czdreiief2xcudbw
GET https://markdownregistry.com/api/v1/resolve?ref=painhardcore/pstack/swarm
GET https://markdownregistry.com/api/v1/blob/4024aa0026b39faba00150e45a67ebe2efc1e3a05cd013371d8dd34d91970ce8
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
painhardcore/pstack · .opencode/skills/architect/SKILL.md · Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use…
painhardcore/pstack · .opencode/skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
painhardcore/pstack · .opencode/skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
painhardcore/pstack · .opencode/skills/create-verification-skill/SKILL.md · Generate a project-local verification skill that drives your app the way a user does — any language, framework, or…
painhardcore/pstack · .opencode/skills/figure-it-out/SKILL.md · Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a…
painhardcore/pstack · .opencode/skills/how/SKILL.md · Explain how a subsystem works, trace a runtime flow, or determine where code and ownership belong before making a…
painhardcore/pstack · .opencode/skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
painhardcore/pstack · .opencode/skills/principle-boundary-discipline/SKILL.md · Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI…
cursor/plugins · harness/pstack/claude-code/skills/swarm/SKILL.md · Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage…
cursor/plugins · pstack/skills/swarm/SKILL.md · Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage…
michael-denyer/pstack-claude · plugins/pstack/skills/swarm/SKILL.md · Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage…
backnotprop/pstack · skills/swarm/SKILL.md · Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage…
zaxbyhub/opencode-swarm · .claude/skills/swarm/SKILL.md · Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task…
zaxbyhub/opencode-swarm · .agents/skills/swarm/SKILL.md · Codex adapter for enabling a higher-rigor swarm-like workflow in the current Codex thread. Use when the user asks for…
guaardvark/guaardvark · .agents/skills/swarm/SKILL.md · Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a…