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 bryanjbelanger/desktop-hypervisor-mcp --skill hv-vmgit clone --depth 1 https://github.com/bryanjbelanger/desktop-hypervisor-mcpWrote 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/bryanjbelanger/desktop-hypervisor-mcp/hv-vm)<a href="https://agentmods.dev/skills/bryanjbelanger/desktop-hypervisor-mcp/hv-vm"><img src="https://agentmods.dev/badge/skills/bryanjbelanger/desktop-hypervisor-mcp/hv-vm/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/bryanjbelanger/desktop-hypervisor-mcp/hv-vm"><img src="https://agentmods.dev/badge/skills/bryanjbelanger/desktop-hypervisor-mcp/hv-vm.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 | $0.00065 | $0.00650 |
| Opus 5 | $0.00032 | $0.00325 |
| Sonnet 5 | $0.00013 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
hv-vm 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provision a VM
Preflight
Requires the desktop-hypervisor MCP server: confirm mcp__hypervisor__provider
is available (loaded or deferred). Missing → stop; it's on the MCP Registry as
io.github.bryanjbelanger/desktop-hypervisor-mcp (binaries/.mcpb on the repo's
latest release); register with
claude mcp add --scope user hypervisor -- <binary> and restart the session.
provider action=list shows each installed hypervisor's readiness and
remediation. One ready provider is auto-selected; several → ask the user, then
pass provider= on every call.
Check existing state first (vm_info action=list) and never reuse a taken name.
Choose the path
- Catalog image (preferred) —
artifact action=catalog, thenartifact action=fetch image=<entry>(adddry_run=trueto preview version/size/checksum). The artifact resolves per provider — VirtualBox and VMware each get an image they can import. Verified wherever the publisher ships a digest; warn the user when output says UNVERIFIED. - User-supplied machine file (
.ova/.ovf/.vmx) → import path. - ISO install (no appliance exists) → create + attach path.
Import path
vm_lifecycle action=import path=<file> vm=NAME- Size it:
vm_config action=resources vm=NAME cpus=C memory_mb=M(defaults 2/2048 for a headless server; ask only if the workload is ambiguous) - Running hypervisors inside the VM?
vm_config action=nested_virt vm=NAME vm_lifecycle action=start vm=NAME(headless default;gui=truefor a console)
ISO path
vm_lifecycle action=create vm=NAME cpus=C memory_mb=M disk_gb=G guest_os=<id>(firmware=efiwhere the OS needs it)vm_config action=attach_iso vm=NAME iso=<path>- Start; the user drives the OS installer unless the ISO is auto-installing (kickstart/autoinstall — see hv-network's make_iso/repack_iso for seeding).
Verify & report
vm_info action=running for state, action=show vm=NAME for detail,
action=ip vm=NAME for the address (works for agentless guests via DHCP
leases). Report name, specs, provider, how to reach it — and stock credentials
if a Vagrant-sourced image was used (usually vagrant/vagrant; advise changing).
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 · 53 lines · 65 tokens per session scan A 531e568d5094
hv-vm is a skill published in the GitHub repository bryanjbelanger/desktop-hypervisor-mcp (0 stars, last pushed 23d ago), licensed MIT. It adds 65 tokens to every session and 650 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…