Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/openrouterlabs/spawn/codexnpx skills add OpenRouterLabs/spawn --skill codexgit clone --depth 1 https://github.com/OpenRouterLabs/spawnWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.00513 |
| Opus 5 | $0.00008 | $0.00257 |
| Sonnet 5 | $0.00003 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
spawn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to spawn — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
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
-pfor non-interactive output (NOT--print, NOT--headless) - Add
--dangerously-skip-permissionsto skip approval prompts on child VMs - Never try
which claudeorfindto 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 childrenspawn 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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 52 lines · 15 tokens per session scan A c210319fd066
spawn is a skill published in the GitHub repository OpenRouterLabs/spawn (233 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 513 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to spawn, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-resend
Add Resend (email) channel integration via Chat SDK.
customize
Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.