mac-it-guy-pro AGENTS.md

A set of working rules for a Mac troubleshooting plugin whose diagnostic recipes may inspect a real computer's files, devices, network, and user profile.

In plain words
What is it for?
Use it when adding or checking diagnostic recipes, testing against real or simulated Mac data, choosing matching rules, and verifying privacy, language, and release requirements.
Why use it?
It reduces privacy risks during testing by requiring hidden personal values, synthetic fixtures where possible, and placeholders in tracked files.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/xiaolai/mac-it-guy-pro/agents-md
Clone the repo
git clone --depth 1 https://github.com/xiaolai/mac-it-guy-pro

Made for: Codex, OpenCode.

Per session 1,786 This file is loaded in full into every session.
When invoked 1,786 The same file — it is already loaded in full.
Security scan D 4 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 $0.01786 $0.01786
Opus 5 $0.00893 $0.00893
Sonnet 5 $0.00357 $0.00357
Haiku 4.5 $0.00179 $0.00179

Measured 3d ago against content hash b865d9383ca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

mac-it-guy-pro AGENTS.md scanned grade D with 4 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- the remote-sudo ask stays on `hit`, because the sudo it looks for is inside

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

later commands as its own: `rm -rf /tmp/x && mkdir -p /tmp/x/bin` was denied

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`ssh host 'bash <(curl …)'` is real and prose containing a literal pipeline

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

fs=subprocess.run(['git','ls-files','-z'],capture_output=True,text=True).stdout.split('\0')
AGENTS.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working conventions for this repo

Shared by Claude, Codex, and any other agent working on mac-it-guy-pro.

Privacy discipline when testing against a real machine

This plugin's recipes can only be trusted if they are run, and running them means pointing diagnostic commands at a real person's Desktop, Downloads, Documents, network, and profile. That verification has caught real bugs and should continue. The output of it is the hazard, not the act.

Binding rules:

  1. Never print raw file names, paths, device names, addresses, or profile values from the operator's real directories. Print counts, aggregates, pass/fail, or field labels with values suppressed. wc -l instead of the listing; grep -c instead of the match; "OK (value suppressed)" instead of the value.
  2. Never write a real person's name, employer, address, or file name into any tracked file — not into documentation, not into an example, and above all not into a test fixture. Use placeholders: Ada, Zoë, example.com, MacBook Air M2. A placeholder tests exactly as well.
  3. Prefer synthetic fixtures over the live machine. Build a temporary directory with the shape you need. Reach for the operator's real data only when the question is specifically "does this behave correctly against real-world mess," and then apply rule 1.
  4. Nothing personal in commit messages. They are the hardest place to scrub, because removing them rewrites published history.
  5. Redact before quoting. When a real value must be discussed to explain a finding, describe its shape ("a company name", "a 12-character prefix") rather than reproducing it.

Rule of thumb: this plugin instructs the IT guy to keep MAC addresses, private IPs, and device inventories out of the user's own profile. Hold the development process to the same standard it imposes on the product.

English only

All tracked content is English: documentation, prompts, skills, commands, code, comments, test fixtures, and commit messages. Values a user supplies at runtime may be in any language; nothing checked in may be.

Read the full file on GitHub · 119 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. 3d ago First seen · 119 lines · 1,786 tokens per session scan D b865d9383ca1

Subscribe to this mod's changes

mac-it-guy-pro AGENTS.md is an instructions file published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,786 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.