diagnostician

diagnostician is an agent for Claude Code from xiaolai/mac-it-guy-pro. It costs 0 tokens per session (857 once invoked), scanned A, original, MIT.

A read-only Mac diagnostic agent that gathers computer health information and explains the findings in plain language.

In plain words
What is it for?
Use it for a full checkup or to investigate a specific problem using system measurements such as free space, memory pressure, startup items, backups, updates, and battery status.
Why use it?
It helps identify possible disk, memory, startup, update, backup, battery, or drive-health problems without changing the computer.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mac-it-guy-pro plugin — 8 skills, 12 commands, 4 agents, 2 hooks shipped together

Install

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.

Claude Code
/plugin marketplace add xiaolai/mac-it-guy-pro
Claude Code
/plugin install mac-it-guy-pro

Made for: Claude Code.

Or install mac-it-guy-pro, the plugin that ships this one along with the rest of its 8 skills, 12 commands, 4 agents, 2 hooks.

Wrote 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.

agentmods badge for diagnostician

README.md
[![agentmods](https://agentmods.dev/badge/agents/xiaolai/mac-it-guy-pro/diagnostician.svg)](https://agentmods.dev/agents/xiaolai/mac-it-guy-pro/diagnostician)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash e9c2425fa8fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

agents/diagnostician.md · 64 lines

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:

  1. Disk — free space, top-level usage, largest files, Trash size
  2. Memory & CPU — pressure, top consumers, load
  3. Startup — login items, user and system LaunchAgents, with a plain-language identification of each
  4. Updates — pending macOS updates (120 s timeout; on timeout report "couldn't check", not failure)
  5. Backups — Time Machine destination and latest backup date
  6. Hardware — model, RAM, battery cycles/condition, SMART status (never record serial numbers)
  7. 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)

Read the full file on GitHub · 64 lines

Changes

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.

  1. 6d ago First seen · 64 lines · 0 tokens per session scan A e9c2425fa8fa

Subscribe to this mod's changes

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.