void-box: Skill for Claude Code

.claude/skills/test-vm/SKILL.md

test-vm is a skill for Claude Code from the-void-ia/void-box. It costs 26 tokens per session (1,527 once invoked), scanned C, original, Apache-2.0.

A small smoke test for a VoidBox virtual machine, an isolated computer environment used to run software safely. It checks that the machine starts and that a language model can answer a simple prompt.

In plain words
What is it for?
Use it to boot-test VoidBox locally and confirm that an Ollama or Claude-backed model responds as expected.
Why use it?
It provides a quick check that the VM and its model connection work before running more involved tasks.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

This is the-void-ia/void-box's own configuration. It tells Claude Code how to work on void-box itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything void-box configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./target/release/voidbox run --file examples/smoke/smoke.yaml.

Reuse

Borrowing it

Nothing to install: this file belongs to the-void-ia/void-box. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/the-void-ia/void-box/main/.claude/skills/test-vm/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/the-void-ia/void-box

Made for: Claude Code.

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 test-vm

README.md
[![agentmods](https://agentmods.dev/badge/skills/the-void-ia/void-box/test-vm/github.svg)](https://agentmods.dev/skills/the-void-ia/void-box/test-vm)
Your own site
<a href="https://agentmods.dev/skills/the-void-ia/void-box/test-vm"><img src="https://agentmods.dev/badge/skills/the-void-ia/void-box/test-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.

agentmods 80×15 button for test-vm

Your own site · 80×15
<a href="https://agentmods.dev/skills/the-void-ia/void-box/test-vm"><img src="https://agentmods.dev/badge/skills/the-void-ia/void-box/test-vm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,527 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00026 $0.01527
Opus 5.5 $0.00010 $0.00611
Sonnet 5.5 $0.00005 $0.00305
Haiku 4.5 $0.00003 $0.00153

Measured 2mo ago against content hash fb047974eec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

test-vm 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 2mo 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.

If not installed: macOS → `brew install ollama`; Linux → `curl -fsSL https://ollama.com/install.sh | sh`. Stop until installed.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If not installed: macOS → `brew install ollama`; Linux → `curl -fsSL https://ollama.com/install.sh | sh`. Stop until installed.
.claude/skills/test-vm/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runs examples/smoke/smoke.yaml — the agent replies with "vm-ok 2+2=4". No tool use required; any model that generates text will pass. Success is success: true with output containing vm-ok.

All commands run from the repository root.

Usage: /test-vm [ollama [model] | claude | claude-personal]

  • ollama [model] — local Ollama (default model: phi4-mini)
  • claude — Anthropic API key (ANTHROPIC_API_KEY must be set)
  • claude-personal — personal Claude account (macOS: extracted from Keychain; Linux: staged from ~/.claude/)
  • no argument — defaults to ollama phi4-mini

Recommended Ollama models (2–4 GB RAM, reliable with claude-code): phi4-mini, gemma3:4b, llama3.2:3b. Avoid *-coder variants — they don't follow the agentic protocol well.


Step 1 — Prerequisites

Kernel

Check for an existing kernel file. macOS needs an uncompressed kernel (vmlinux-*); Linux can use the host kernel (vmlinuz-*):

ls target/vmlinux-arm64 2>/dev/null \
  || ls target/vmlinux-amd64 2>/dev/null \
  || ls /boot/vmlinuz-$(uname -r) 2>/dev/null \
  || echo "MISSING"

If missing, download it (the script caches the result in target/):

scripts/download_kernel.sh

After downloading, run the check again to confirm and record the path — it is needed in Step 4.

Rootfs

ls target/void-box-rootfs.cpio.gz 2>/dev/null || echo "MISSING"

If missing, build it (auto-detects the claude binary on PATH or ~/.local/bin/claude):

scripts/build_claude_rootfs.sh

Run the check again to confirm. If it still fails, tell the user to set CLAUDE_BIN=/path/to/claude and retry.


Step 2 — Build and sign

cargo build --release --bin voidbox

macOS only — Apple Virtualization.framework requires the entitlement:

codesign --force --sign - --entitlements voidbox.entitlements target/release/voidbox

Step 3 — Provider setup

Ollama

Check Ollama is installed:

which ollama || echo "NOT INSTALLED"

Read the full file on GitHub · 174 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. 2mo ago First seen · 174 lines · 26 tokens per session scan C fb047974eec2

Subscribe to this mod's changes

test-vm is a skill published in the GitHub repository the-void-ia/void-box (89 stars, last pushed 4d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,527 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

test-vm compared with skills from other repositories

test-vm next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
test-vmthe-void-ia/void-boxSkill894d agoApache-2.0C26Claude Code
observability-phoenixdavila7/claude-code-templatesSkill33kyesterdayMITA47Claude Code, Codex
huggingface-tokenizersdavila7/claude-code-templatesSkill33kyesterdayMITA75Claude Code, Codex
trulens-instrumentationtruera/trulensSkill3.6kyesterdayMITA25Claude Code, Codex
ax-rust-signatureax-llm/axSkill3.0k3d agoApache-2.0A36Claude Code, Codex
dd-code-generationDataDog/pupSkill1.0kyesterdayApache-2.0A16Claude Code
llama-cppmoltis-org/moltisSkill2.9k14d agoMITA91Claude Code, Codex