sandbox

Commands for managing isolated development environments, such as Docker or Lima virtual machines. A sandbox is a separate environment where tools and code can run with less impact on the main machine.

In plain words
What is it for?
Use them to build or pull a sandbox image, generate a customizable Dockerfile, or stop Lima virtual machines when they are no longer needed.
Why use it?
They simplify building, downloading, customizing, and stopping the environments used to run coding agents.

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/raine/workmux/sandbox
Clone the repo
git clone --depth 1 https://github.com/raine/workmux
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,958 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 $0.00006 $0.01958
Opus 5 $0.00003 $0.00979
Sonnet 5 $0.00001 $0.00392
Haiku 4.5 $0.00001 $0.00196

Measured 2d ago against content hash 25793e244ca0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandbox 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/src/content/docs/reference/commands/sandbox.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commands for managing sandbox functionality across container (Docker/Podman/Apple Container) and Lima backends.

Container commands

sandbox build

Build the sandbox container image locally (two-stage: base + agent).

workmux sandbox build

Builds the image locally for the configured agent. This is an alternative to using the pre-built image from ghcr.io/raine/workmux-sandbox. Most users should use workmux sandbox pull instead.

sandbox pull

Pull the latest sandbox image from the container registry.

workmux sandbox pull

Pulls the pre-built image for the configured agent from ghcr.io/raine/workmux-sandbox:{agent}. This is the recommended way to get and update the sandbox image.

sandbox init-dockerfile

Export a customizable Dockerfile for building your own sandbox image.

workmux sandbox init-dockerfile [--force]

Options:

  • --force - Overwrite existing Dockerfile

Creates a Dockerfile.sandbox in the current directory with the base system setup (Debian, git, workmux) and agent-specific installation (e.g., Claude Code) combined into a single file.

Lima commands

sandbox stop

Stop Lima VMs to free resources.

# Interactive mode - show list and select VM
workmux sandbox stop

# Stop specific VM
workmux sandbox stop <vm-name>

# Stop all workmux VMs
workmux sandbox stop --all

# Skip confirmation prompt
workmux sandbox stop --all --yes

Arguments:

  • <vm-name> - Name of the VM to stop (optional, conflicts with --all)

Options:

  • --all - Stop all workmux VMs (those starting with wm- prefix)
  • -y, --yes - Skip confirmation prompt

This command helps you stop running Lima VMs created by workmux to free up system resources. When run without arguments, it shows an interactive list of running workmux VMs for you to choose from. The command will ask for confirmation before stopping any VMs unless --yes is provided.

Notes:

  • This command only works with Lima backend and requires limactl to be installed
  • Only running VMs are shown in interactive mode
  • If a specified VM is already stopped, the command reports this and exits successfully
  • Non-interactive environments (pipes, scripts) require --all or a specific VM name

Read the full file on GitHub · 235 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 · 235 lines · 6 tokens per session scan A 25793e244ca0

Subscribe to this mod's changes

sandbox is a command published in the GitHub repository raine/workmux (2,351 stars, last pushed today), licensed MIT. It adds 6 tokens to every session and 1,958 once invoked, about $0.0000 per session on Opus 5. 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.