agentleFS
ariana-dot-devariana-dot-dev/cloud-sandbox-vm-skills/skills/docker-sandbox/SKILL.md

docker-sandbox

Skill2 starsChanged 5 months agoMITView on GitHub

Run Docker and containers in a cloud sandbox — a full root Ubuntu VM with Docker preinstalled and real kernel access, so `docker build`/`docker run`/compose all work (unlike isolate-based sandboxes that can't run Docker). 4 vCPU / 8 GB / 80 GB, per-second billing. Use to build images, run compose stacks, or test containers off-host.

  • Pipes a download into a shell
  • Reads credentials

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    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:

    Use this when a task needs Docker: building an image, running docker compose, or testing a container.

    line 8

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Docker sandbox (Box)

Use this when a task needs Docker: building an image, running docker compose, or testing a container. Many sandboxes (V8 isolates, restricted microVMs) can't run Docker at all — Box is a full VM with Docker preinstalled, so it just works.

Why Box

  • Docker preinstalled, real machine — docker build, docker run, compose stacks.
  • 80 GB disk — room for images and layers.
  • Cheap & isolated — per-second billing, separate from the host.

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 < ./clone-and-build.sh   # git clone + docker build
box ssh "$box_id" -- "cd /project && docker compose up -d"
box ssh "$box_id" -- "host 8080"                       # expose the running container
box delete "$box_id" --json

Limits

EU-only; 100 active VMs soft cap; disk-level snapshots (containers don't survive stop/resume — restart compose after resume).

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.