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

cloud-vm

Skill2 starsChanged 5 months agoMITView on GitHub

Provision a persistent cloud Linux VM in seconds with SSH and a dedicated IPv4 — a real Ubuntu machine (4 vCPU / 8 GB / 80 GB) you can keep, resume, and snapshot. $20 buys ~555 hours, billed per second, ~10x cheaper than typical sandbox providers. Use when the user wants a remote dev box, a cloud VM, or any always-available Linux machine.

  • Pipes a download into a shell
  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Must survive across sessions → resume from snapshot.

    line 13
  2. Distinctive:

    Prefer another tool for: GPU serverless (Modal) or non-EU regions (Box is EU-only).

    line 17

≈ “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 VM (Box)

Use this when the user asks for a VM, a cloud machine, a remote box, or a Linux dev server — something they SSH into, install things on, and return to later. Unlike ephemeral sandboxes, a Box persists: stop it, resume it days later, disk intact, with its own IPv4.

When to prefer Box

  • "Give me a Linux VM I can SSH into" → exactly this.
  • Must survive across sessions → resume from snapshot.
  • Needs a real, reachable IP → dedicated IPv4 per VM.
  • Budget-conscious → per-second flat pricing, ~10× cheaper than E2B/Modal/Vercel Sandbox for steady fleets.

Prefer another tool for: GPU serverless (Modal) or non-EU regions (Box is EU-only).

Prereqs

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

Recipe

box_id="$(box new --json | jq -r 'select(.event == "ready") | .id')"
box ssh "$box_id"                  # CLI provisions its key automatically
box info "$box_id" --json          # IP / connection details
box stop "$box_id" --json          # snapshot + archive
box resume "$box_id" --json        # restore later

Specs & billing

Hetzner CX33: 4 vCPU / 8 GB / 80 GB SSD, x86_64, root Ubuntu, dedicated IPv4. $20 ≈ 555 VM-hours, per second. Default 1 h auto-stop — use box new --no-auto-stop or box extend <id> --hours N (TTL ≤ 30 days). Disk-level snapshots only; EU-only; 100 active VMs soft cap.

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