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 xiaolai/mac-it-guy-pro --skill macos-recipesgit 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/macos-recipes)<a href="https://agentmods.dev/skills/xiaolai/mac-it-guy-pro/macos-recipes"><img src="https://agentmods.dev/badge/skills/xiaolai/mac-it-guy-pro/macos-recipes.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 5.1 | $0.00062 | $0.02513 |
| Opus 5 | $0.00031 | $0.01256 |
| Sonnet 5 | $0.00012 | $0.00503 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
macos-recipes 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Recipes
Exact commands, expected output shape, and gotchas. Use these verbatim rather than improvising — the gotchas are the value.
Scope note
This skill covers command mechanics only — what to run, what the output means, and where each command lies or fails silently. It deliberately holds no policy.
Read the companions for the rules that govern using these commands: mac-it-guy-pro:it-core for the safety contract (Trash instead of delete, dry-run first, undo manifests, admin work handed to the user), mac-it-guy-pro:machine-profile for what may be written down afterwards, and mac-it-guy-pro:toolbox-contract for turning a recipe into a tool the user keeps. Network measurement lives in mac-it-guy-pro:home-network, not here.
A recipe in this file is never authority to run it — the contract decides that.
Diagnostics (read-only)
Disk
- Free space:
df -h /— use theAvailandCapacitycolumns of the/System/Volumes/Dataor/line. - What's big (one level):
du -x -h -d 1 ~ 2>/dev/null | sort -rh | head -15 - Top 10 largest files:
find ~ -xdev -type f -size +500M -not -path "*/Library/*" 2>/dev/null -exec du -h {} + | sort -rh | head -10 - Gotcha:
duover the whole home folder takes 1–4 minutes on a full disk. Say so before running; use a 300000 ms timeout. - Gotcha: macOS "purgeable" space makes Finder and
dfdisagree. If they differ, trustdfand explain the difference in one sentence.
Memory & CPU
- Memory pressure:
memory_pressure | tail -1— reports "System-wide memory free percentage". - Top consumers:
ps -Ao pid,pcpu,pmem,comm -r | head -8 - Load:
uptime
Hardware identity (for the profile)
- Model & RAM:
system_profiler SPHardwareDataType | grep -E "Model Name|Model Identifier|Memory|Chip"— do NOT record the serial number line. - macOS version:
sw_vers - Battery:
system_profiler SPPowerDataType | grep -E "Cycle Count|Condition|Maximum Capacity" - SMART status:
diskutil info disk0 | grep SMART— anything other than "Verified" is a 🔴 finding.
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 · 144 lines · 62 tokens per session scan A aaa44e317d1b
macos-recipes is a skill published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,513 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
c-bluetooth
Manage Bluetooth devices on macOS using the blucli (blu) CLI. List paired and available devices, connect to headphones/speakers/keyboards, and disconnect devices by name or MAC address.
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.
solidworks-vibecad
A planning guide for turning natural-language mechanical design requests into structured, parameterized SolidWorks plans that can be reviewed before execution.
eide
A build tool for EIDE projects, an embedded-development extension for Visual Studio Code. It finds EIDE project settings and builds firmware using ARM CC or GCC.
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…