swarm is agent-read markdown (skill) from ulises-jeremias/agent-toolkit: Launch an Agent Toolkit swarm from a natural language request using agent-toolkit swarm CLI.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Swarm
Launch a production Agent Toolkit swarm from any natural language request via the `agent-toolkit swarm` CLI. Herdr is the default UI for an excellent interactive experience; tmux is the isolated fallback.
## When to use
- User says "launch a swarm", "start a swarm", "swarm this task", or describes parallel/team work that benefits from multiple agents.
- Any task that mentions swarm, pair/team/full, Herdr, tmux, or worktree-per-writer.
- User wants to reuse an existing swarm run for a new request (same windows, new handoff).
## Prerequisites
- `agent-toolkit` installed and on PATH (`agent-toolkit swarm doctor` should pass).
- For Herdr: `herdr` CLI installed (`herdr --version`); Herdr daemon running.
- For tmux: `tmux` installed; isolated socket is `agent-toolkit-swarm-<run-id>`.
- Run inside a Git repo (or pass `--workspace /path/to/repo`).
- Optional: `~/.config/agent-toolkit/swarm.yaml` for model-profile mapping (`economy` → `opencode/mimo-v2.5-free`, `balanced` → provider default).
## Workflow
### 1. Inspect intent
Extract from the user prompt:
- **Task**: free-form objective (if missing, start swarm ready for interactive input).
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_jlvkl7k44rnv53z5
GET https://markdownregistry.com/api/v1/resolve?ref=ulises-jeremias/agent-toolkit/swarm
GET https://markdownregistry.com/api/v1/blob/d55d5a4a775637462f11d9ee494891fa02041f2046a94ea38921ce2c801c093e
Your agent 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.
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/adr/SKILL.md · WHAT — Create and maintain Architecture Decision Records (ADRs) per the process. Covers when
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/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…
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/bug/SKILL.md · WHAT - Draft and review bugs using the Bug Template; classifies whether an issue should be
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/c4-model/SKILL.md · WHAT — C4 model methodology (Context, Container, Component, Code) guidance — what to draw at each level, when, and how…
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/chrome-devtools/SKILL.md · Use Chrome DevTools MCP to control and inspect a live Chrome instance for network, console, performance, rendering, and…
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…
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…
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…
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…
