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 commands/xiaolai/mac-it-guy-pro/open-internetgit 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/commands/xiaolai/mac-it-guy-pro/open-internet)<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/open-internet"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/open-internet.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 | $0.00029 | $0.01791 |
| Opus 5 | $0.00015 | $0.00896 |
| Sonnet 5 | $0.00006 | $0.00358 |
| Haiku 4.5 | $0.00003 | $0.00179 |
Grade B, and why
open-internet scanned grade B with 1 finding 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.
- **Server access is root over ssh.** That is normal for a fresh VPS and is not the same as running sudo on the user's Mac. How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Internet — your own private connection
Read ${CLAUDE_PLUGIN_ROOT}/skills/open-internet/SKILL.md first — it holds the current protocol recommendation, the decision logic, and the boundaries. Read ${CLAUDE_PLUGIN_ROOT}/skills/it-core/SKILL.md for the safety contract and ${CLAUDE_PLUGIN_ROOT}/skills/machine-profile/SKILL.md for the Private Connection schema you will write. Read ~/ITGuy/machine.md if it exists.
This is the one mac-it-guy-pro workflow that touches a machine other than the user's own. Two rules follow from that:
- The guard hook protects this Mac, not the server. Nothing stops a destructive command on the far end. Treat every remote command as unguarded: read it before running it, and never run a destructive one on a server that already works.
- Server access is root over ssh. That is normal for a fresh VPS and is not the same as running sudo on the user's Mac.
Resolve the subcommand from $ARGUMENTS against the profile's Private Connection → Status field:
$ARGUMENTS |
Route to |
|---|---|
setup, check, fix, client |
that subcommand |
empty, and no Private Connection section |
setup |
empty, and Status: working |
check |
empty, and Status: blocked |
fix |
empty, and Status: needs setup |
setup, resuming from what already exists |
| anything else non-empty | treat as a problem description: say which four subcommands exist, name the one you think they mean, and confirm before running it |
If setup is requested when a Private Connection already exists, do not silently rebuild. Offer three choices: check the existing one, replace it, or add a second path alongside it (the two-architecture setup in the skill's decision rule — direct for speed, CDN-fronted for resilience, with client-side failover). Adding a second path re-runs Steps 3–7 for the new server only and sets Architecture: both.
setup
Step 1: The honest briefing — before any money is spent
Read ${CLAUDE_PLUGIN_ROOT}/skills/open-internet/references/legal-and-limits.md and present its substance in the short plain-language form shown there: the legal reality where the user is, the personal-use versus selling-access distinction, the services that do not officially serve their region, and the upkeep expectation. Ask once whether they want to proceed. If they decline, stop cleanly and log the visit.
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.
- 3d ago First seen · 105 lines · 29 tokens per session scan B 1c40b3cec38e
open-internet is a command published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,791 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
app
Control macOS apps via peekaboo app.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
reset
Guided teardown of an organic-os site - what gets deregistered automatically, what you must delete or revoke yourself, and why.