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.
npx skills add ariana-dot-dev/cloud-sandbox-vm-skills --skill docker-sandboxgit clone --depth 1 https://github.com/ariana-dot-dev/cloud-sandbox-vm-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/docker-sandbox)<a href="https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/docker-sandbox"><img src="https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/docker-sandbox/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/docker-sandbox"><img src="https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/docker-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.00374 |
| Opus 5 | $0.00043 | $0.00187 |
| Sonnet 5 | $0.00017 | $0.00075 |
| Haiku 4.5 | $0.00009 | $0.00037 |
Grade C, and why
docker-sandbox scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl -fsSL https://box.ascii.dev/install | sh`, then `box login "$BOX_API_KEY" --json`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -fsSL https://box.ascii.dev/install | sh`, then `box login "$BOX_API_KEY" --json`. What it actually says
Docker sandbox (Box)
Use this when a task needs Docker: building an image, running docker compose, or testing a container. Many sandboxes (V8 isolates, restricted microVMs) can't run Docker at all — Box is a full VM with Docker preinstalled, so it just works.
Why Box
- Docker preinstalled, real machine —
docker build,docker run, compose stacks. - 80 GB disk — room for images and layers.
- Cheap & isolated — per-second billing, separate from the host.
Prereqs
curl -fsSL https://box.ascii.dev/install | sh, then box login "$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).
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.
- 8d ago First seen · 33 lines · 85 tokens per session scan C 24d58169e1dd
docker-sandbox is a skill published in the GitHub repository ariana-dot-dev/cloud-sandbox-vm-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 374 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
container-layer
Authors and caches a personalized container environment from a Dockerfile- like spec, as a single layer or as a composition of independently cached layers. Use when the user mentions "container layer", "Containerfile", "custom container", "cache my installs", "composable layers", "uv shim", or wants package…
using-webctl
Browser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web scraping, or headless Chrome in container environments.
manage-mounts
Configure which host directories agent containers can access. View, add, or remove mount allowlist entries. Triggers on "mounts", "mount allowlist", "agent access to directories", "container mounts".
devops-engineer
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing…
offensive-container-escape
Container escape and breakout techniques targeting Docker, containerd, and Podman runtimes. Covers privileged container breakout via host filesystem mount and nsenter, Docker socket abuse through /var/run/docker.sock, Linux capability exploitation including CAPSYSADMIN, CAPSYSPTRACE, and CAPNETADMIN, cgroup v1…
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…