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/automategit 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/automate)<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/automate"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/automate.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 | $0.00020 | $0.00916 |
| Opus 5 | $0.00010 | $0.00458 |
| Sonnet 5 | $0.00004 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
automate 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automate — turn a chore into a tool you keep
Read ${CLAUDE_PLUGIN_ROOT}/skills/it-core/SKILL.md and ${CLAUDE_PLUGIN_ROOT}/skills/toolbox-contract/SKILL.md first — the safety contract and the toolbox contract are binding. Read ~/ITGuy/machine.md if it exists. If uname is not Darwin, say this version supports Mac only and stop. If ~/ITGuy/ does not exist, create it (with toolbox/, undo/, reports/) — automate may be a user's first command.
Step 1: Clarify the chore into a spec
$ARGUMENTS is the chore in the user's words ("every week I rename my scans", "I always convert HEIC photos before emailing them"). If $ARGUMENTS is empty, ask first: "What's the chore? Describe it the way you'd describe it to a friend." — then continue. Turn the description into a spec — at most one AskUserQuestion round for whatever is genuinely ambiguous:
- Input: which folder/files, identified how
- Action: what happens to them, including the exact naming/format rule
- Frequency: how often the chore recurs
- Success criteria: one testable sentence — "afterwards, every scan in X is named YYYY-MM-DD-"
Step 2: Apply the acceptance test
The toolbox contract's three criteria: real problem, repeat use, evolvable. A one-off task fails the test — do it directly instead (with the same safety rules), tell the user why no tool was built, log the visit, done.
Step 3: Check the toolbox, then the catalogue
Read ~/ITGuy/toolbox.json. An existing tool covers the chore → show its README and how to run it, bump nothing, done. A near-miss exists → offer evolving it instead of duplicating.
Then check ${CLAUDE_PLUGIN_ROOT}/skills/toolbox-contract/references/pattern-catalogue.md: if the described chore matches a catalogue pattern, build that recipe rather than improvising one. The catalogue entries carry gotchas learned the expensive way — keeping originals when converting HEIC, labelling a fallback date as a fallback, confirming duplicates by checksum before trusting a filename. Improvising past them reinvents the bugs.
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 · 53 lines · 20 tokens per session scan A 9c85f2f67759
automate is a command published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 916 once invoked, about $0.0001 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.
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.
compile
Compile a FIBER decision context (world + query) and report the oracle verdict, omission accounting, and certificate digest faithfully.