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/profile)<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/profile"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/profile/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/profile"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/profile.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 | $0.00022 | $0.01497 |
| Opus 5.5 | $0.00009 | $0.00599 |
| Sonnet 5.5 | $0.00004 | $0.00299 |
| Haiku 4.5 | $0.00002 | $0.00150 |
Grade A, and why
profile 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profile — auditable memory
Read ${CLAUDE_PLUGIN_ROOT}/skills/machine-profile/SKILL.md first — schema and update rules are binding. If uname is not Darwin, say this version supports Mac only and stop. If ~/ITGuy/machine.md does not exist, say there is no profile yet and point to /mac-it-guy-pro:onboard — then stop.
Resolve the subcommand from $ARGUMENTS; empty means show.
show
Print ~/ITGuy/machine.md verbatim, then a three-line footer:
- How to reach him: list both triggers — the
Summon:value and, when anIT guy:name is set, the derived_<name>— noting that capitalisation is irrelevant to either. - Visits on record: count of lines in
~/ITGuy/visits.log, with the date of the first and the latest. - Memory health: run
bash "${CLAUDE_PLUGIN_ROOT}/scripts/lint-profile.sh"and summarise it in one line — counts by severity, nothing more. If it reports anyCRITICAL, say so first and offerreviewimmediately; a stored secret is not a footnote. - "This file is the IT guy's entire memory of this machine. Edit it or delete any line — whatever it says is what I'll believe next visit. What I've stopped believing is in
history.md."
review — the deep memory audit
Run the linter first — it does the mechanical half deterministically:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/lint-profile.sh"
It emits SEVERITY|rule|location|message per finding (exit 0 clean, 1 findings, 2 no profile) and checks what prose cannot enforce: stored secrets, untagged facts, conclusions with no retest date or method, overdue retests, told-facts over a year old, stale measurements, an unverified or 60-day-old connection status, a summon word missing its underscore, the 120-line cap, malformed ledger lines, and demoted beliefs missing from history.md.
Act on CRITICAL findings before anything else and before showing the profile. A stored private IP, MAC address, UUID, share link, or password is a privacy failure, not a tidiness issue: remove it from machine.md and history.md, write a redacted ledger event that records the removal without repeating the value, and tell the user plainly what was stored and that it is gone.
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 · 67 lines · 22 tokens per session scan A 26a0a587e979
profile is a command published in the GitHub repository xiaolai/mac-it-guy-pro (6 stars, last pushed 16d ago), licensed MIT. It adds 22 tokens to every session and 1,497 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
remember
Write-side memory: stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Use when something worth persisting across sessions was just learned or decided. To search or read existing memory, invoke memory; to debug retrieval internals…
memory
Read-side memory operations on the knowledge graph: search past decisions and patterns, load session context, view decision timelines, render Mermaid graph visualizations. Subcommands: search, load, history, viz, status. Use when finding or reviewing what memory already holds. For storing new knowledge instead, invoke…
dream
Nightly memory consolidation: prunes stale entries, merges duplicates, resolves contradictions, rebuilds the MEMORY.md index. Use when memory files accumulated over many sessions need cleanup. New decisions get stored by remember; searches run through memory; internals live in memory-fabric.
set-context
Set the client context so all subsequent analyses are automatically tailored — store client name, industry, size, geography, and key facts.
query
Structured frontmatter queries using yq.
context
Analyze and optimize Claude Code's context configuration (analyze, optimize, or reset).