Skip to content
Skills Library
AI & agents · Automation

swarm

/swarm

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

Licence
MIT
Last repository change
06.11.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 06.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

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

Triggers from the description

swarm this
Original author description

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

How it works

  1. Start
  2. Phase A: Frame
  3. Phase B: Fan out
  4. Phase C: Aggregate
  5. Phase D: Report
Original SKILL.md headings · 40 lines, 384 words
SKILL.md preview
---
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."
---

Read [the Codex runtime contract](../../CODEX.md) once before applying this workflow.


# 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. Pick the optional `swarm workers` model from models.json, otherwise inherit the parent. For a model race, name the supported configured model for each arm and disclose unavailable model diversity. Follow CODEX.md for spawning.
4. 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

Use available Codex subagent tools and queue workers within the slot limit. Give each writer an isolated worktree and exact starting ref. Cloud VMs are not available by implication; see CODEX.md.

Use available Codex subagent tools and queue workers within the slot limit. Give each writer an isolated worktree and exact starting ref. Cloud VMs are not available by implication; see CODEX.md.

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. A worker that can prove a defect reports `ISSUES` and lists every issue it can prove, not only the first.

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.

## 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.
Files in this package (2)
  • SKILL.md 2 KB
  • agents/openai.yaml 1 KB

Versions

RepositoryScoreLicence
This page · robansuini/pstack-codex90MIT
iha2/superlite100MIT
Ovich/charrette100MIT
marcopesani/swarm-skill100MIT
guaardvark/guaardvark100MIT
requie/endostack100MIT
Sup-Film/pstack-omp-lean100MIT
ialameh/sift-coder100MIT
ALDY711/MCP-AI-XYZ95MIT

Database snapshot: 13.11.2026 · package version 20f9cc80c415 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90st-swarm
    Fan out N parallel workers on slices of a job or on a race, collect every result, and return one evidence-backed report. Use for wide coverage, audits, races between approaches or exploration, or for /st-swarm, 'swarm this', 'split this across workers'.
  • 90ds-swarm
    Fan out N parallel workers on slices of a job or on a race, collect every result, and return one evidence-backed report. Use for wide coverage, audits, races between approaches or exploration, or for /ds-swarm, 'swarm this', 'split this across workers'.
  • 90agents-swarm
    Fan out N parallel subagent workers in one turn, aggregate their results, and report PASS, ISSUES, or BLOCKED per worker. Use for /agents-swarm, "swarm this", parallel coverage across slices, races between approaches, or broad exploration.
  • 90kyoshi-formation
    Suki's fan formation for parallel work. Every Kyoshi Warrior holds a set position, and the squad returns one report. Use for swarm, /swarm, "swarm this", fanning out N parallel workers, coverage sweeps, races between identical briefs, review gauntlets, verifier lanes, and exploration partitions.
  • 100code-swarm
    Split one task into independent slices, run a parallel worker for each, collect the results through files, and return one status report with every gap named. Use when the user asks to swarm a task, or wants one worker per package, file or commit, or many independent checks at…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.