How do I install the Ps Swarm skill?

Run npx skillmds@latest add gannonh/ps-swarm in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ps Swarm safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ps Swarm?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ps Swarm free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Ps Swarm?

gannonh (@gannonh) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ps Swarm by gannonh — Agent Skill

Name: Ps Swarm
Author: gannonh

File contents

Swarm

Harness adaptation

Read the harness adaptation contract before delegating work, asking structured questions, selecting models, or locating harness state.

Fan out N parallel subagents. 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 cloud concurrency limit.
Pick the worker model from swarm workers in .agents/pstack/models.json when present. Otherwise use medium. For a model race, name each arm's model up front.
Give each worker its own writable output when it writes. Use a worktree, branch, or /tmp/swarm-<slug>/worker-<n>/.

Phase B: Fan out

Spawn all N workers through the harness's delegation mechanism. Start them concurrently when supported, use the configured tier, and isolate them from each other's writes. Keep a worker local only when it needs resources on the user's computer.

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

---name: ps-swarmdescription: Fan out N parallel workers, drain them, and return one report. Use for ps-swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.license: MIT. See LICENSE.txt---# Swarm## Harness adaptationRead [the harness adaptation contract](../ps-poteto-mode/references/harness-adaptation.md) before delegating work, asking structured questions, selecting models, or locating harness state.Fan out N parallel subagents. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.## StartOpen a todolist with one entry per phase before launching anything.1. Frame2. Fan out3. Aggregate4. Report## Phase A: Frame1. 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. Pick the worker model from `swarm workers` in `.agents/pstack/models.json` when present. Otherwise use `medium`. For a model race, name each arm's model 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 outSpawn all N workers through the harness's delegation mechanism. Start them concurrently when supported, use the configured tier, and isolate them from each other's writes. Keep a worker local only when it needs resources on the user's computer.When a worker must start from a non-default pushed branch, pass the required 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: AggregateRead 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: ReportReturn one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.

Frequently asked questions

Ps Swarm