warmup

A command that prepares a remote or local machine for later use. It provisions or claims the machine, waits for SSH and setup services, then keeps the reservation active without running a command.

In plain words
What is it for?
Use it to reserve machines from providers such as AWS or Azure, local containers, SSH hosts, or supported desktop environments, with options for operating system, architecture, browser, GPU, and other setup needs.
Why use it?
It removes the waiting and setup work before a remote task begins. Later commands can reuse a machine that is already ready.

Command

Install

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.

agentmods
npx agentmods add commands/openclaw/crabbox/warmup
Clone the repo
git clone --depth 1 https://github.com/openclaw/crabbox
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,731 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04731
Opus 5 $0.00000 $0.02365
Sonnet 5 $0.00000 $0.00946
Haiku 4.5 $0.00000 $0.00473

Measured 2d ago against content hash 5fcf1a776297, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

warmup 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.

docs/commands/warmup.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

warmup

crabbox warmup leases a box and waits until it is ready: it provisions (or claims) a remote machine, waits for SSH plus the Crabbox bootstrap plumbing to come up, then keeps the lease so later commands can reuse it. Unlike run, warmup runs no command — it just hands you a ready box.

crabbox warmup --class beast
crabbox warmup --provider aws --class beast --market on-demand
crabbox warmup --provider aws --os ubuntu:26.04 --desktop --browser --desktop-env wayland
crabbox warmup --provider azure --class beast
crabbox warmup --provider azure --arch arm64 --class fast
crabbox warmup --browser
crabbox warmup --tailscale
crabbox warmup --slug update-flow-smoke
crabbox warmup --provider aws --lease-id cbx_abcdef123456 --slug update-flow-smoke
crabbox warmup --provider local-container --lease-id cbx_abcdef123456 --slug update-flow-smoke
crabbox warmup --pond alpha --slug db
crabbox warmup --provider aws --target windows --desktop
crabbox warmup --provider azure --target windows
crabbox warmup --provider aws --target macos --desktop --market on-demand --type mac2.metal
crabbox warmup --actions-runner
crabbox warmup --provider ssh --target macos --static-host mac-studio.example.com
crabbox warmup --provider ssh --target windows --static-host win-dev.example.com --static-work-root 'C:\crabbox' --browser

Output

On success warmup prints two lines on stdout — the lease summary and the ready SSH endpoint — followed by a total-duration line:

leased cbx_0123456789ab slug=swift-crab provider=hetzner server=... type=... ip=... idle_timeout=30m expires=...
ready ssh=root@... :2222 network=public workroot=/work/crabbox
warmup complete total=42.1s

The canonical lease ID is cbx_...; the friendly slug is an auto-generated <adjective>-<noun> handle (or a normalized --slug you requested). Reuse either with later run, status, ssh, inspect, and stop commands. Scripts should prefer the canonical ID. Add --timing-json to emit a final JSON timing record (provider, lease ID, slug, total duration, exit code) on stderr.

Read the full file on GitHub · 378 lines

Changes

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.

  1. 2d ago First seen · 378 lines · 0 tokens per session scan A 5fcf1a776297

Subscribe to this mod's changes

warmup is a command published in the GitHub repository openclaw/crabbox (1,343 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,731 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.