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 skills/xiaolai/mac-it-guy-pro/machine-profilenpx skills add xiaolai/mac-it-guy-pro --skill machine-profilegit clone --depth 1 https://github.com/xiaolai/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/skills/xiaolai/mac-it-guy-pro/machine-profile)<a href="https://agentmods.dev/skills/xiaolai/mac-it-guy-pro/machine-profile"><img src="https://agentmods.dev/badge/skills/xiaolai/mac-it-guy-pro/machine-profile.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 | $0.00066 | $0.02912 |
| Opus 5 | $0.00033 | $0.01456 |
| Sonnet 5 | $0.00013 | $0.00582 |
| Haiku 4.5 | $0.00007 | $0.00291 |
Grade A, and why
machine-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 4d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Machine Profile — memory that expires honestly
The profile is the IT guy's memory. It is plain Markdown the user can open, read, and edit — never a hidden database. Everything in it must be something they could verify themselves.
The failure mode this schema exists to prevent: ten commands write here and, without discipline, none retire anything. A profile that only grows becomes a landfill of half-true statements, and stale beliefs are worse than no beliefs — a conclusion drawn a year ago and never retested silently biases every future diagnosis toward a cause that may no longer exist.
Provenance decides expiry — tag every fact
How a fact was learned determines how it dies. Tag each one inline; the tag is part of the line, not metadata elsewhere.
| Class | Written as | Lifecycle |
|---|---|---|
| Measured | (measured 2026-07-29) |
Never trusted as current. Disk space, memory, macOS version, battery. The stored number is a baseline to compare against, not a fact — any command needing the value re-reads it. Refresh the date whenever re-read |
| Observed | (observed 2026-07-29) |
Cheap to re-observe: file counts, folder habits, dominant file types. Refresh on the next command that looks |
| Told | (you told me 2026-07-29) |
The user's own words: name, work, goals, preferences. Only the user may invalidate these. Never auto-expire, never quietly rewrite |
| Concluded | (concluded 2026-07-29, retest by 2026-10-29) |
The dangerous class. A diagnosis, a quirk, a cause-and-effect the IT guy inferred. Every one carries a retest date and a way to retest — see below |
| Resolved | moves to history.md |
No longer live. Demoted with the date and what closed it |
A fact with no tag is a bug. When you find one, tag it with what you can establish and today's date, or demote it.
Conclusions must carry their own retest
This is the rule that keeps the profile honest. A conclusion without a retest is a rumour with a date on it.
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.
- 4d ago First seen · 169 lines · 66 tokens per session scan A 8781d1791c83
machine-profile is a skill published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 2,912 once invoked, about $0.0003 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 skills, from other repositories
vellum-memory-v2-migration
Perform a one-time migration from memory v1, to memory v2, which was introduced in 0.8.0.
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
context-drop
Tiny Swift CLI that reads the focused app's text selection via the macOS Accessibility API. Sutando.app's "drop context" action (hotkey configurable via state/hotkeys.json) shells out to this binary to capture what you have highlighted.
context-reconstruct
Re-anchor on the durable record (current-track, live owner thread, pending-questions, relay, buildlog) before acting on anything that depends on earlier context. Read, do not recall.
session-recap
Reconstruct what happened in a past core session — from a high-level summary down to verbatim owner quotes — by reading the raw session transcripts (complete, crash-proof, unbiased), not the curated relay/handoff notes.