Someone messaged me today asking how long it would take GHL Command to do a complete build from a system spec doc and approx how many tokens it would consume. She needs Voice AI, Conversational AI, chat widgets, multiple pipelines, multiple calendars, workflows… you name it. Good question! The spec doc was 31 pages written by an obvious IT specialist, a little over my head and about 3x the size of my typical client builds. So… let’s find out! I fed her spec doc into GHL Command and told it to make it happen. I am recording the whole thing, with a side by side view of Claude Code in the terminal and GHL. I also told it to use any new findings to build new features into GHL Command, so we walk away from this test with more functionality. I’ll drop the results and an edited video if we get enough interest. Drop a BUILD comment below if you want to see how it turned out!

Last week I posted a poll here. I was excited about it. GHL Command was about to get the ability to create and delete client sub-accounts for you. Riyaz R replied with something better than a yes. He said he keeps two things manual no matter what: user access and sub-account management. His reason: in case of prompt injection, or the agent going rogue. And he asked that if we ship it, we make it optional so he could turn it off. That is not resistance. That is free security architecture. So instead of shipping the exciting default, we treated his threat model as the design requirement, then generalized it: any tool could be a liability in somebody's threat model. So every tool got an off switch. How we built it: • Wrote the design plan first, then had an independent adversarial AI attack the plan. It found 18 issues, including a critical one: five tools registered through a side path the off switch would have silently missed. • Built it, then ran a second adversarial audit on the code. Two more findings. Fixed both. • Proved it on the real shipped binary: 5 live proofs, 736 tests. What shipped in v3.56.0, live now: • Sub-account create and delete is OFF by default. You opt in with GHL_ENABLE_ACCOUNT_ADMIN=1, and the setup wizard asks first (default is No). • A universal off switch: GHL_DISABLED_TOOLS and GHL_DISABLED_MODULES can disable any tool or any module. A disabled tool never registers. The AI cannot call it or even see it, so prompt injection has nothing to grab. • There is deliberately no way to re-enable a tool from inside a conversation. Turning something back on takes a config edit and a full restart. In other words, a human. • You cannot brick yourself: 4 recovery tools ignore denial, with a warning. • health_check now shows your gating state and catches typos, so a misspelled tool name warns loudly instead of silently failing open. The lesson: excitement ships features. Caution ships trust. AI tools with write access to your business need human-owned kill switches, and they should exist before the incident, not after.

Would you like the ability for GHL Command to actually Create and Delete new client sub-accounts for you?

Not sure why I have the softest claude ai. View pics (it wont do what I want)

Welcome in. You're a founding member, and I don't take that lightly. Quick on what this is. GHL Command is the room for agency owners who use AI to actually run their operations, not just market with it. I run a healthcare agency on this exact stack every day: the GHL Command MCP, Claude, and a small team of named agents. This is where I build it in public, drop the prompts and templates I'm using, and answer your GoHighLevel questions directly. What your membership includes, plainly: - The GHL Command tool (your license) at the founding rate of $97/mo, locked as long as you stay subscribed. - This community: the build-in-public room, the prompts and templates, and me answering questions. - Every new tool we ship, automatically, at no extra cost while you're a member. Billing lives in your account, not here. You can manage or cancel anytime. If you cancel, the license and your spot here wind down together. Simple. Your first 20 minutes: 1. Open the Start Here course in the Classroom. It gets GHL Command installed and gives you a real win in about 10 minutes (point Claude at one of your sub-accounts and have it tell you what's silently broken). 2. Come back and introduce yourself below: who you are, how many sub-accounts you run, and the one GHL task you're most tired of doing by hand. 3. Read the first war story I pinned: "The $5,000 pipeline ID mistake every GHL agency owner makes." It's the bug that started all of this. That's it. Get the tool running, get your first win, then tell me what you want me to build next. This thing grows around what you actually need. — Jerry