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 commands/xiaolai/mac-it-guy-pro/onboardgit 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/commands/xiaolai/mac-it-guy-pro/onboard)<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/onboard"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/onboard.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 | $0.00034 | $0.01782 |
| Opus 5 | $0.00017 | $0.00891 |
| Sonnet 5 | $0.00007 | $0.00356 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
onboard 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 4d 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.
Onboard — the IT guy's first visit
Read ${CLAUDE_PLUGIN_ROOT}/skills/it-core/SKILL.md and ${CLAUDE_PLUGIN_ROOT}/skills/machine-profile/SKILL.md first — the safety contract and profile schema are binding. If uname is not Darwin, say this version supports Mac only and stop.
Principle: the machine is the interview. The user likely knows their computer only through Office-style apps — do not ask them questions about it. A real IT guy looks at the machine: the Desktop, the Downloads folder, and the backup status say more than any questionnaire. Everything is observed with read-only scans; the user is asked one short round of questions and nothing about their computer.
Tone: a friendly professional making a house call — no jargon, no lectures, no quiz.
Step 1: Check for an existing profile
If ~/ITGuy/machine.md exists, show its Updated: line and use AskUserQuestion: update the existing profile (default) or start over. Starting over moves the old machine.md to the Trash first (never rm — safety contract rule 2).
Step 2: Observe the machine
Dispatch the mac-it-guy-pro:diagnostician agent (via Task) for all six diagnostic areas plus the behavior area: Desktop composition and screenshot pileup, Downloads size/age/composition, dominant file types across Documents, Desktop, and Downloads. The behavior evidence is what replaces interview questions — it reveals what the user actually does and which chores are piling up.
Step 3: The one question round — names and language
Introduce yourself in two plain sentences: "I'm your IT guy — I look after this Mac and remember everything between visits. Call me out anytime, in any conversation, by typing _it — the underscore is what keeps the everyday word 'it' from summoning me by accident."
Then ask — one AskUserQuestion call carrying all three questions, not three rounds:
- "What would you like to call me?" Offer two or three plain first names and "No name needed". The built-in Other option takes anything. Say in one clause that naming him also gives him a second way to be called.
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.
- 4d ago First seen · 71 lines · 34 tokens per session scan A 1191f20a8d48
onboard is a command published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,782 once invoked, about $0.0002 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 commands, from other repositories
app
Control macOS apps via peekaboo app.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
reset
Guided teardown of an organic-os site - what gets deregistered automatically, what you must delete or revoke yourself, and why.