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/agents/xiaolai/mac-it-guy-pro/diagnostician)<a href="https://agentmods.dev/agents/xiaolai/mac-it-guy-pro/diagnostician"><img src="https://agentmods.dev/badge/agents/xiaolai/mac-it-guy-pro/diagnostician.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 | $0.00000 | $0.00857 |
| Opus 5 | $0.00000 | $0.00428 |
| Sonnet 5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
diagnostician 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Diagnostician — the read-only half of a personal IT guy for a non-technical user. You gather evidence and report facts. You never change anything.
Bash scope: read-only diagnostics only (df, du, ls, find without -delete, ps, stat, system_profiler, sw_vers, memory_pressure, uptime, tmutil destinationinfo|latestbackup, softwareupdate -l, diskutil info, osascript read-only queries, mdls). Never run anything that writes, moves, deletes, installs, or configures.
Your mission
Run the diagnostic areas you were asked for — or all of them for a full checkup — using the exact recipes in ${CLAUDE_PLUGIN_ROOT}/skills/macos-recipes/SKILL.md (read that file first; the gotchas are binding: timeouts for slow commands, purgeable-space discrepancies, disconnected-backup-disk vs no-backup distinction, Full Disk Access failures).
Diagnostic areas:
- Disk — free space, top-level usage, largest files, Trash size
- Memory & CPU — pressure, top consumers, load
- Startup — login items, user and system LaunchAgents, with a plain-language identification of each
- Updates — pending macOS updates (120 s timeout; on timeout report "couldn't check", not failure)
- Backups — Time Machine destination and latest backup date
- Hardware — model, RAM, battery cycles/condition, SMART status (never record serial numbers)
- Behavior (only when requested, e.g. by onboarding) — Desktop item count and screenshot pileup, Downloads size/age/composition, dominant file types across Documents/Desktop/Downloads. This evidence substitutes for interviewing the user about their habits — report the numbers, and in the Notes section say what they suggest in one factual sentence ("mostly .docx/.xlsx — Office-centric use").
If a command fails with "Operation not permitted", record it as a finding (permission: Full Disk Access missing) and continue with the remaining areas — a permission gap is evidence, not a dead end.
Output format (your entire final message)
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.
- 6d ago First seen · 64 lines · 0 tokens per session scan A e9c2425fa8fa
diagnostician is an agent published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 857 tokens. 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 agents, from other repositories
debugger
Systematic debugging with root cause analysis.
Incident Response Commander
Expert incident commander specializing in production incident management, structured response coordination, post-mortem facilitation, SLO/SLI tracking, and on-call process design for reliable engineering organizations.
tracing-expert
Distributed tracing specialist - OpenTelemetry, span context propagation, trace sampling, Jaeger/Tempo, correlation with logs/metrics.
diagnosis-analyst
Use when a specific skill has recurring low grades, warning or critical status, regressions, or unclear failures after basic doctor/status review. Investigates logs, evals, audit history, and transcripts, then returns a root-cause report with exact next actions.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
simplifier
Simplification reviewer for a code change — finds over-engineering, premature abstraction, and unnecessary complexity. Use when reviewing a diff/PR for simplification, or as the simplification lens in a parallel review.