agentleFS
OpenRouterTeamOpenRouterTeam/spawn/skills/codex/SKILL.md

spawn

Skill251 starsChanged 5 months agoApache-2.0View on GitHub

Create child cloud VMs with AI coding agents using the spawn CLI

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Spawn — Create Child VMs

You have the spawn CLI installed. Use it to provision cloud VMs with AI agents.

Provision a Child VM

spawn <agent> <cloud> --headless --output json --prompt "task description"

Agents: claude, codex, cursor, openclaw, opencode, kilocode, hermes, junie Clouds: hetzner, digitalocean, aws, gcp, sprite

Returns JSON: {"status":"success","ip_address":"...","ssh_user":"root","server_id":"..."}

Running Prompts on Child VMs

--headless only provisions — to run work on the child, SSH in with bash -lc:

# Claude Code (use -p, NOT --print or --headless)
ssh -o StrictHostKeyChecking=accept-new root@<ip> "bash -lc 'claude -p --dangerously-skip-permissions \"your prompt\"'"

# Codex CLI
ssh -o StrictHostKeyChecking=accept-new root@<ip> "bash -lc 'codex --quiet \"your prompt\"'"

IMPORTANT — do NOT waste tokens rediscovering these:

  • Always use bash -lc — agent binaries are in ~/.local/bin/ which is only on PATH in login shells
  • Claude uses -p for non-interactive output (NOT --print, NOT --headless)
  • Add --dangerously-skip-permissions to skip approval prompts on child VMs
  • Never try which claude or find to locate binaries — they are always at ~/.local/bin/<agent>
  • Never create non-root users to work around permission issues — just use -p

Managing Children

  • spawn list --json — see running children
  • spawn delete --name <name> --yes — tear down a child VM (headless)
  • spawn tree — see the full spawn tree

Context

  • You are running inside a spawned VM (SPAWN_DEPTH is set)
  • Cloud credentials are pre-configured — no auth prompts
  • OpenRouter billing is shared with the parent

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.