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/toolboxgit clone --depth 1 https://github.com/xiaolai/mac-it-guy-proWhat 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 | $0.00025 | $0.01038 |
| Opus 5 | $0.00013 | $0.00519 |
| Sonnet 5 | $0.00005 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
toolbox 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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toolbox — the tools you own
Read ${CLAUDE_PLUGIN_ROOT}/skills/it-core/SKILL.md and ${CLAUDE_PLUGIN_ROOT}/skills/toolbox-contract/SKILL.md first. If uname is not Darwin, say this version supports Mac only and stop.
If ~/ITGuy/toolbox.json does not exist or holds no tools, do not simply send the user away to /mac-it-guy-pro:automate — a user with an empty toolbox usually has no idea what is automatable, so telling them to go describe a chore is the dead end this catalogue exists to fix. Instead run the suggestion pass below and let them choose from something concrete.
Resolve the subcommand from $ARGUMENTS; empty means list.
list
Read ~/ITGuy/toolbox.json and render:
| Tool | What it does | Built | Last used | Runs | Stage |
|---|
Then check the evolution ladder's triggers: any tool with 5+ runs still at script stage gets one line offering the upgrade. If the registry references a folder that no longer exists, flag it as broken and offer remove.
Staleness check — a toolbox rots as quietly as a profile does:
- Unused for 180+ days → offer removal once. If declined, do not raise it again for another 180 days.
- Broken by a system update → run each tool's dry-run and report any that now error. A tool the user believes works but doesn't is worse than no tool: offer repair via
evolve, and mark it in the registry so it is not silently recommended meanwhile. - A tool whose pattern no longer fires (its chore stopped happening) is not stale — it is probably working. Say so rather than offering removal.
Suggestion pass. Read ${CLAUDE_PLUGIN_ROOT}/skills/toolbox-contract/references/pattern-catalogue.md and run its signals, including the 30-day recency companions. Skip any pattern whose id appears in declined, and any whose id already appears as a pattern field on a built tool. Per the catalogue's per-command table this context allows up to three offers — the user came here to look at tools — highest count first, each a one-line offer containing the observed number, chosen via AskUserQuestion with a "none of these" option.
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.
- 2d ago First seen · 58 lines · 25 tokens per session scan A aae5a691e89f
toolbox is a command published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,038 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.
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
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.