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 agentmods add skills/ariana-dot-dev/cloud-sandbox-vm-skills/linux-server-sshnpx skills add ariana-dot-dev/cloud-sandbox-vm-skills --skill linux-server-sshgit 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/linux-server-ssh)<a href="https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/linux-server-ssh"><img src="https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/linux-server-ssh.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.00401 |
| Opus 5 | $0.00044 | $0.00200 |
| Sonnet 5 | $0.00018 | $0.00080 |
| Haiku 4.5 | $0.00009 | $0.00040 |
Grade D, and why
linux-server-ssh scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
box ssh "$box_id" -- "sudo apt-get install -y nginx && sudo systemctl enable --now nginx" 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
Linux server over SSH (Box)
Use this when the task needs an actual Linux server the user can ssh/scp into: hosting a service, running a daemon, or a remote workstation.
Why Box
- First-class SSH —
box ssh <id>opens a session; the CLI handles keys. SCP works too. - Dedicated IPv4 + full TCP/UDP — a real addressable host, not a loopback-only sandbox.
- Root Ubuntu —
apt installanything; Docker preinstalled. - Cheap & persistent — per-second billing, resumes from snapshot, ~10× cheaper than E2B/Modal at steady state.
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 "$box_id" # interactive shell
box ssh "$box_id" -- "sudo apt-get install -y nginx && sudo systemctl enable --now nginx"
box info "$box_id" --json # shows the IP
Honest limits
EU-only region; 100 active VMs soft cap; disk-level snapshots (running processes don't survive stop/resume). For 1000+ concurrent servers or <500 ms boot, use Daytona/E2B/Modal.
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.
- 4d ago First seen · 33 lines · 88 tokens per session scan D 02350a9f5ab3
linux-server-ssh 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 88 tokens to every session and 401 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, 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
all-deploy
Deploys any web app, API, or agent to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Detects Next, Vite, Astro, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP server, Claude Agent SDK script, Python worker, Dockerized, and static projects; routes to Vercel, Railway…
otel-collector-config
Use when authoring, debugging, or reviewing an OpenTelemetry Collector (otelcol) configuration — defining receivers/processors/exporters/connectors, wiring service pipelines, choosing between the core and contrib distributions, or exporting to OTLP/Prometheus/Loki/Tempo/Mimir. Also use when a Collector starts but no…
connect-domain
Connect a user's own custom domain (subdomain e.g. recipes.brand.com via CNAME, or apex e.g. brand.com via A record) to a site already deployed on simple-host. Use when a user wants their site served from their own domain with automatic HTTPS, or wants a private/password-protected site (privacy is offered only on a…
azure-support-ticket
File and manage Azure support tickets from the terminal via the az CLI support extension. Use when the user wants to open, draft, list, inspect, or follow up on an Azure support case - "file an Azure support ticket", "open a case with Microsoft", "raise a ticket for this Azure issue", "check my Azure support tickets"…
artifact-organizer-share
Deploy a previously rendered Artifact Organizer HTML file to Vercel and return a live shareable URL. Use whenever the user asks to "share", "publish", "deploy", or "send" a Artifact Organizer output. Requires the vercel CLI (npm i -g vercel, then vercel login) and the artifact-organizer skill for the share script.
gcloud-gpu-agent
Launch GPU VMs on Google Cloud (GCE) and run commands on them over SSH. Use when the user wants to spin up a cloud GPU instance (L4/T4/V100/A100/H100), train or run code on a remote GPU, push a local repo to a VM, stream remote logs, or manage (create/ssh/stop/delete) GPU VMs. Triggers: "launch a GPU VM", "run this on…