Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add xiaolai/mac-it-guy-pro/plugin install 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/fix)<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/fix"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/fix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/fix"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/fix.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00897 |
| Opus 5.5 | $0.00010 | $0.00359 |
| Sonnet 5.5 | $0.00005 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
fix 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 1mo 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.
Fix — diagnose before treat
Read ${CLAUDE_PLUGIN_ROOT}/skills/it-core/SKILL.md first — the safety contract is binding, especially: diagnose before treat, admin work handed to the user, verify after fix. Read ~/ITGuy/machine.md if it exists — Live Conclusions may already explain the symptom. If uname is not Darwin, say this version supports Mac only and stop.
Step 1: Restate the symptom
$ARGUMENTS is the user's description ("it's slow", "the fan is loud", "I can't find my files"). If $ARGUMENTS is empty, first ask — AskUserQuestion with common symptom options (slow, noisy/hot, out of space, something else) — before proceeding. Restate the symptom in one sentence and confirm anything ambiguous with AskUserQuestion — when did it start, is it constant or occasional, one app or everything. One round of questions at most.
Step 2: Gather evidence
Dispatch the mac-it-guy-pro:diagnostician agent (via Task) scoped to the areas the symptom implicates (slowness → memory, CPU, disk, startup; noise/heat → CPU, battery; space → disk). Cross-check its findings against the profile's Live Conclusions.
Step 3: Present the diagnosis
- What's going on: one plain-language paragraph tying evidence to symptom.
- Confidence: state it as high / moderate / low, and what would confirm it if not high.
- Options table:
| Option | What it does | Risk | Undoable? |
|---|
Always include "do nothing for now" as a row. If the honest answer is hardware or an Apple-side problem, say so and describe what to tell the repair shop — a good IT guy knows when it's not a software fix.
Step 4: Fix only what the user picks
Use AskUserQuestion for the choice, then apply exactly that option. Anything requiring admin rights is handed to the user: the exact command, the ! prefix instruction, and one sentence on what it does (safety contract rule 6). Anything requiring a restart: tell them why and let them do it when ready — never restart the machine yourself.
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.
- 1mo ago First seen · 53 lines · 25 tokens per session scan A 822378667c81
fix is a command published in the GitHub repository xiaolai/mac-it-guy-pro (6 stars, last pushed 16d ago), licensed MIT. It adds 25 tokens to every session and 897 once invoked, about $0.0001 per session on Opus 5.5. 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
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…
ci-debug
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…
wiki-lint
Health-check the wiki for orphans, broken links, and quality issues.
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
bug-report
Converts a raw bug report from production into a structured, severity-classified item and routes it to the right next step.
verify
Run the full verification suite (build, type-check, tests, lint) via a fresh-context verification-runner subagent; reports evidence paths. Read-only by default; opt-in '--fix' runs a bounded auto-fix loop (max 2 cycles). Use before marking featurelist.json status as 'pass'.