vm-lab

A guide for testing GUI automation and permission prompts inside a clean macOS virtual machine. It covers Parallels, Peekaboo-like tools, screenshots, and host-side checks; a virtual machine is an isolated computer running inside another computer.

In plain words
What is it for?
Use it to test macOS GUI automation, TCC privacy prompts, screenshots, typing, clicking, performance, and two-way validation in a disposable VM.
Why use it?
It provides safety rules and a repeatable way to verify what happens inside the test machine without relying only on the tool being tested. This helps avoid changing the host computer or losing independent evidence.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/steipete/agent-scripts/vm-lab
Any agent
npx skills add steipete/agent-scripts --skill vm-lab
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-scripts

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,662 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00025 $0.01662
Opus 5 $0.00013 $0.00831
Sonnet 5 $0.00005 $0.00332
Haiku 4.5 $0.00003 $0.00166

Measured 2d ago against content hash fec816569176, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

vm-lab scanned grade B with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/parallels_type.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

'sudo -u steipete -H /bin/zsh -lc '\''source ~/.zprofile 2>/dev/null || true; uname -a'\'''
skills/vm-lab/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VM Lab

Use this when the task needs a clean macOS VM to test GUI automation, TCC prompts, screenshot capture, clicking, typing, performance, or "two-way validation" of Peekaboo-like tools.

Core idea: run the tool under test inside the guest, but verify it from outside the guest with Parallels screenshots and host-side observations. Do not close apps you do not own.

Safety Rules

  • Treat the VM snapshot as disposable, not the host.
  • Never print secrets. If op is needed, follow the 1Password skill and run it only inside tmux.
  • Prefer fresh app windows you create yourself: TextEdit, a local HTML test page, or a small test app.
  • Avoid modifying host state except temporary screenshots under /tmp.
  • For git repos inside the VM, use HTTPS remotes and normal branch discipline.

VM Discovery

List VMs:

prlctl list --all

Get VM status/IP:

prlctl list --info "macOS Tahoe"

Run guest commands as Peter:

prlctl exec "macOS Tahoe" \
  'sudo -u steipete -H /bin/zsh -lc '\''source ~/.zprofile 2>/dev/null || true; uname -a'\'''

Capture an independent host-side screenshot:

prlctl capture "macOS Tahoe" --file /tmp/vm-reference.png
sips -g pixelWidth -g pixelHeight /tmp/vm-reference.png

TCC / GUI Attribution

For macOS Screen Recording and Accessibility, the responsible process matters.

  • prlctl exec is headless and can fail to produce useful Screen Recording attribution.
  • Launch the test command from a visible terminal app in the guest when Screen Recording is involved.
  • Ghostty works as a GUI terminal if installed.
  • After a first failed capture, check System Settings > Privacy & Security > Screen & System Audio Recording.
  • permissions status run through prlctl exec may still report Screen Recording false after Ghostty is allowed; validate Screen Recording by rerunning the capture from Ghostty.

Open the Screen Recording pane:

prlctl exec "macOS Tahoe" \
  'sudo -u steipete -H open "x-apple.systempreferences:com.apple.preference.security?Privacy_ScreenCapture"'

Read the full file on GitHub · 173 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 173 lines · 25 tokens per session scan B fec816569176

Subscribe to this mod's changes

vm-lab is a skill published in the GitHub repository steipete/agent-scripts (6,590 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,662 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens