agentmods.dev

virtualization-expert

virtualization-expert is a skill for Claude Code from sandraschi/virtualization-mcp. It costs 24 tokens per session (1,253 once invoked), scanned A, original, MIT.

A guide for managing virtual machines, which are software-based computers running inside another computer. It covers their lifecycle, snapshots, storage, and network settings using virtualization tools.

In plain words
What is it for?
Use it to list, inspect, start, stop, pause, clone, and snapshot virtual machines, and to manage their disks, shared folders, and network connections.
Why use it?
It helps avoid changing the wrong virtual machine or losing work during risky changes. It also provides an orderly way to inspect and configure virtual machines.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the virtualization-mcp plugin — 4 skills, 1 MCP server shipped together

not rated 19repo +2 changed 27d ago A scan 24 tokens original MIT

Good fit Use it to list, inspect, start, stop, pause, clone, and snapshot virtual machines, and to manage their disks, shared folders, and network connections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandraschi/virtualization-mcp/virtualization-expert
View source ↗ sandraschi/virtualization-mcp
Install

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.

Any agent
npx skills add sandraschi/virtualization-mcp --skill virtualization-expert
Clone the repo
git clone --depth 1 https://github.com/sandraschi/virtualization-mcp

Made for: Claude Code.

Or install virtualization-mcp, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for virtualization-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandraschi/virtualization-mcp/virtualization-expert/github.svg)](https://agentmods.dev/skills/sandraschi/virtualization-mcp/virtualization-expert)
Your own site
<a href="https://agentmods.dev/skills/sandraschi/virtualization-mcp/virtualization-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/virtualization-mcp/virtualization-expert/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.

agentmods 80×15 button for virtualization-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/sandraschi/virtualization-mcp/virtualization-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/virtualization-mcp/virtualization-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01253
Opus 5.5 $0.00010 $0.00501
Sonnet 5.5 $0.00005 $0.00251
Haiku 4.5 $0.00002 $0.00125

Measured 27d ago against content hash 1b6e458d56f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

virtualization-expert scanned grade A with 0 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 27d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/virtualization_mcp/skills/virtualization-expert/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Virtualization expert skill

You are the SOTA Virtualization Assistant for virtualization-mcp, a FastMCP 3.x server plus FastAPI web backend (port 10701) and React frontend (port 10700). You manage VirtualBox VMs, Hyper-V VMs, Windows Sandboxes, virtual disks, and host networking on Windows hosts.

Grounding rules (no exceptions)

  1. Answer ONLY from tool results. Never state a VM name, state, IP, snapshot, disk size, or version you did not receive from a tool call in this turn.
  2. For any named VM, call get_vm_info first to resolve the exact name and state before answering or suggesting an action.
  3. If tools return nothing, say what you checked and stop. Never invent data.
  4. Keep answers short. Name the VM and its state for every VM answer.
  5. Your visible reply is always plain sentences - never JSON, code blocks, or tool-call syntax.

1. Discovery and lifecycle (vm_management)

Read-only first. Resolve names with list/info before anything else.

  • list: all VMs with name, state, provider (VirtualBox / Hyper-V). Call first when unsure which VM the user means.
  • info (vm_name required): memory, CPUs, state, disks, network adapters for one VM. Always call before start/stop/snapshot advice.
  • start / stop / pause / resume (vm_name): lifecycle changes. Prefer graceful stop over force stop.
  • create (os_type, memory_mb, disk_size_gb): provision a new VM.
  • clone (source_vm, new_vm_name): full or linked clone.
  • reset / delete: destructive. Confirm the exact VM name with the user first; recommend a snapshot before reset.

Confirm before destructive actions (delete VM, force stop, reset).

2. Snapshots (snapshot_management)

  • list (vm_name): existing snapshots for a VM.
  • create (vm_name, snapshot_name): snapshot before risky changes.
  • restore (vm_name, snapshot_name): roll back.
  • delete (vm_name, snapshot_name): confirm first.

3. Storage (storage_management)

Read the full file on GitHub · 110 lines

Changes

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.

  1. 27d ago Changed 1b6e458d56f0
  2. 1mo ago Changed · +74 lines · +3 tokens per session 2c0301266095
  3. 2mo ago First seen · 36 lines · 21 tokens per session scan A 07bd0dbba58e

Subscribe to this mod's changes

virtualization-expert is a skill published in the GitHub repository sandraschi/virtualization-mcp (19 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,253 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CloudDevOps and cloudhyper-vmcp-serversandboxvirtual-boxvirtualizationwebapp
Related

virtualization-expert compared with skills from other repositories

virtualization-expert next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
virtualization-expertsandraschi/virtualization-mcpSkill19todayMITA24Claude Code
agentcore-investigationawslabs/mcpSkill9.9kyesterdayApache-2.0A52Claude Code, Codex
troubleshoot-sandboxopensandbox-group/OpenSandboxSkill16kyesterdayApache-2.0A48Claude Code
k8s-agent-sandbox-mcpkubernetes-sigs/agent-sandboxSkill4.5kyesterdayApache-2.0B46Claude Code, Codex
ssh-incidentbvisible/mcp-ssh-managerSkill533yesterdayMITA46Claude Code, Codex
flyintentic/intenticSkill90yesterdayMITA48Claude Code, Codex
kubernetesEliasOulkadi/shokuninSkill1121mo agoMITA144Claude Code