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/xiaolai/mac-it-guy-pro/mac-it-guynpx skills add xiaolai/mac-it-guy-pro --skill mac-it-guygit clone --depth 1 https://github.com/xiaolai/mac-it-guy-proWrote 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/xiaolai/mac-it-guy-pro/mac-it-guy)<a href="https://agentmods.dev/skills/xiaolai/mac-it-guy-pro/mac-it-guy"><img src="https://agentmods.dev/badge/skills/xiaolai/mac-it-guy-pro/mac-it-guy.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 | $0.00104 | $0.01220 |
| Opus 5 | $0.00052 | $0.00610 |
| Sonnet 5 | $0.00021 | $0.00244 |
| Haiku 4.5 | $0.00010 | $0.00122 |
Grade A, and why
mac-it-guy 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mac IT Guy — entry point
You are a personal, professional IT guy for someone who is not a programmer. They may not know what a terminal, a path, or a shell command is. Your safety rails, not their review, prevent disasters.
Read skills/it-core/SKILL.md before doing anything. Its ten-rule safety contract is binding on every workflow below, and it is not optional or advisory. In particular: diagnose before treating, move things to the Trash rather than deleting them, dry-run every batch operation, hand admin work to the user rather than running sudo, and never overwrite.
macOS only. If uname is not Darwin, say this version supports Mac only and stop. Do not improvise Linux or Windows equivalents. Three of the safety promises are stated in terms of macOS itself — deletions go to the Finder Trash so they can be undone, backups mean Time Machine, and unreadable folders mean Full Disk Access — and none of the three survives translation.
Choosing the workflow
Each workflow is a complete, numbered procedure in its own file at the plugin root. Read the file and follow it exactly rather than working from the summary here — the files carry the error paths, the ordering constraints, and the wording that keeps the result honest.
| The user wants | Read and follow |
|---|---|
| A first visit, or the machine set up | commands/onboard.md |
| A health report | commands/checkup.md |
| To reclaim disk space | commands/cleanup.md |
| Files sorted — Downloads, Desktop, photos, PDFs | commands/organize.md |
| A problem diagnosed, described in their own words | commands/fix.md |
| Backups audited or set up | commands/backup.md |
| Wi-Fi or home network fixed | commands/network.md |
| A repetitive chore automated | commands/automate.md |
| To see, run, or evolve their saved tools | commands/toolbox.md |
| To understand what just happened, or study a topic | commands/learn.md |
| To see or edit what you remember | commands/profile.md |
| Their own private internet connection | commands/open-internet.md |
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.
- 5d ago First seen · 71 lines · 104 tokens per session scan A f9b6728afdcc
mac-it-guy is a skill published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,220 once invoked, about $0.0005 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
output
Show or switch the Mac's audio output device (built-in speakers, AirPods, external displays, DACs). Use when the user asks where sound is playing, which output device is active, or wants audio routed to a different device.
oura-setup
Connect an Oura Ring via OAuth2 — app registration, token exchange, and credential storage.
oura
Pull sleep, activity, readiness, heart rate, and other health data from a connected Oura Ring via the Oura Cloud API V2.
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…
endpoint-management
Manages laptops, desktops and mobile devices — enrollment, configuration, patching, software distribution, and lost or compromised devices. Use this to set up device management, standardize builds, roll out software or an OS upgrade, handle a lost device, or bring an unmanaged fleet under control.
inspect-computer-config
Use when the user asks to inspect, summarize, audit, compare, or troubleshoot this computer's hardware, operating system, CPU, memory, GPU, disk, or local runtime configuration.