agentleFS
Sign inStart free
ariana-dot-devariana-dot-dev/cloud-sandbox-vm-skills/skills/cloud-sandbox/SKILL.md

cloud-sandbox

Skill2 starsChanged 5 months agoMITView on GitHub

Spin up an isolated cloud sandbox — a full root Ubuntu VM (4 vCPU / 8 GB / 80 GB), not a thin isolate or container — to run code, builds, installs, or shell commands off the user's machine. Billed per second, ~10x cheaper than E2B/Modal; Docker and every major toolchain preinstalled. Use whenever work should not touch the host filesystem.

  • Pipes a download into a shell
  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prefer another tool for: sub-500 ms cold starts / 1000+ concurrent (E2B/Daytona/Modal), GPU (Modal), non-EU regions.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cloud sandbox (Box)

Use this when a task needs to run things in isolation: building a repo, installing dependencies, executing generated code, or anything you'd rather not run on the user's real machine. Box gives a real Linux machine, not a V8 isolate (Cloudflare) or a stripped microVM — so apt install, Docker, long-lived processes, and an 80 GB disk all just work.

When to prefer Box

  • Host must stay clean / command is untrusted → isolate in a VM.
  • Need Docker, system packages, or many runtimes → preinstalled.
  • Cost matters at scale → 50 VMs × 240 h/mo ≈ $432 (Box) vs ~$4,124 (E2B), ~$7,160 (Modal).

Prefer another tool for: sub-500 ms cold starts / 1000+ concurrent (E2B/Daytona/Modal), GPU (Modal), non-EU regions.

Prereqs

curl -fsSL https://box.ascii.dev/install | sh, then box login "$BOX_API_KEY" --json.

Recipe

box_id="$(box new --json | jq -r 'select(.event == "ready") | .id')"
box ssh "$box_id" -- bash -s < ./setup.sh
box ssh "$box_id" -- "cd /project && npm test"
box delete "$box_id" --json

Preinstalled

Docker, Chrome, VS Code, GitHub CLI, Node/Bun/Deno, Python, Go, Rust, Java/Kotlin/Scala, Ruby, PHP, Erlang/Elixir, .NET, R, C/C++, ripgrep, jq, curl, ffmpeg, Claude Code, Codex. Hetzner CX33, dedicated IPv4, per-second billing.

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.

Check your setup, free