open

A command that prepares an existing remote Crabbox lease for use in an external editor. It prints an SSH connection command and remote folder, then stays running to keep the lease active.

In plain words
What is it for?
Use it to open a Crabbox lease in Zed Remote Projects, connect an editor to the remote folder, or start the handoff from an agent or other process. The command can print human-readable or machine-readable connection details.
Why use it?
It removes the need to manually assemble connection details and keeps the remote workspace available during the editor session. Its JSON output also lets another program read the handoff automatically.

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/open
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 958 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 $0.00958
Opus 5 $0.00000 $0.00479
Sonnet 5 $0.00000 $0.00192
Haiku 4.5 $0.00000 $0.00096

Measured 2d ago against content hash a4b6526cc19c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

open 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/open.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

open

crabbox open prepares an existing SSH-capable lease for an external editor. Select the editor with --editor; Crabbox prints its connection details and remote folder, then keeps the lease active until you press Ctrl-C.

Zed Remote Projects is the first supported editor:

crabbox run --id swift-crab --sync-only
crabbox open --editor=zed --id swift-crab

The default output separates the SSH command and remote folder into labeled, copyable blocks. In Zed, open Remote Projects, select Connect New Server, paste the SSH command, and open the remote folder. Keep crabbox open running for the duration of the editor session.

Automation and agents

Use --json when another process needs to consume the handoff:

crabbox open --editor=zed --id swift-crab --json

Crabbox writes one newline-terminated JSON object to stdout and then remains in the foreground to maintain lease activity. Diagnostics and workspace notices continue to use stderr, so stdout stays machine-readable. An agent can start the command as a child process, decode the first JSON object, use sshCommand and remoteFolder, and keep the child running until the editor session ends.

The versioned crabbox/editor-handoff/v1 object includes:

  • editor and displayName
  • leaseId, sshCommand, and remoteFolder
  • hydratedByActions
  • leaseActivity, which is foreground
  • hardTTLApplies
  • releaseCommand, when the lease has an id

releaseCommand carries the effective non-secret provider and routing flags, so it remains usable when the handoff overrides repository configuration.

Why the command stays running

External editors open their own SSH processes after a connection is added. Those processes do not send Crabbox lease heartbeats. While crabbox open is running, Crabbox keeps coordinator-backed leases heartbeating and marks direct-provider leases running or ready where the provider supports lease touches.

Managed leases with a resolved expiry keep their configured hard TTL while the command is running. Static SSH targets have no Crabbox-enforced hard TTL.

Read the full file on GitHub · 100 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 · 100 lines · 0 tokens per session scan A a4b6526cc19c

Subscribe to this mod's changes

open 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 958 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.