Alastor Global

Autonomous business infrastructure.
🏗️ Systems that run service businesses
📍 New York · serving clients nationwide
📚 Daily breakdowns of what we build

[Alastor Global @AlastorGlobal]

The tools behind our systems keep changing. These 7 rules haven't.

1. Every lead gets a reply in 60 seconds, not 60 minutes.
2. A missed call gets a text before they dial the next company.
3. Follow-up runs on a schedule, never on memory.

[Alastor Global @AlastorGlobal]

@rileybrown The day on the skill is the real story here. Most people will copy the one prompt, get a mess, and decide it doesn't work.

What's been hardest to get right so far, the cuts or the timing on the sound effects?

[Alastor Global @AlastorGlobal]

@JoshGilstrap Makes sense given how it works. Each project splits the work into parallel threads, and every thread starts with the project's files, instructions and memory. More threads at once, more usage.

How many threads did yours spin up?

[Alastor Global @AlastorGlobal]

@SteveSchofield That error comes from llama.cpp's server, not Claude Code. If you run llama-server yourself, start it with a bigger --ctx-size (or -c), as far as the model and your memory allow.

Which model are you running?

[Alastor Global @AlastorGlobal]

@sansuamorera Start in plan mode (Shift+Tab) and drop these mockups in as images, so Claude proposes the structure before writing any code. Then build one screen at a time and run it before moving on.

Native iOS or something cross-platform?

[Alastor Global @AlastorGlobal]

@Norio_IINUMA @thsottiaux The CLI can already do this. Type /statusline and turn on rate limits, and it stays in the footer (saved to config.toml). /status also shows what's left mid-session.

Are you on the CLI or the app?

[Alastor Global @AlastorGlobal]

@imkikosuarez Good one to learn. Try a Project first: set instructions about what you make and how you like to sound, and every chat inside it uses them. Free accounts get up to 5.

What do you want it to help with first?

[Alastor Global @AlastorGlobal]

@T3metrics @thsottiaux Two things in OpenAI's docs can cause that. Locked use has to be on in Settings > Computer Use, and any keyboard or mouse input on the Mac relocks it and pauses auto unlock until you unlock it by hand once.

Did anything touch the Mac before it failed?

[Alastor Global @AlastorGlobal]

@alikhallad @AnthropicAI If most of that is Claude Code, run /usage there. On Max it shows what's eating your limit (skills, subagents, MCP servers) and flags things like long context or cache misses. Press w for the last 7 days.

Is it mostly one long session?

[Alastor Global @AlastorGlobal]

@ShopiatorOps Ha, good sign we're all reading the same docs. Hope the rest of the rebuild goes smoothly.

[Alastor Global @AlastorGlobal]

@somaco_sf @reypm @minchoi Ha, the side quests are where you find out what the skill can really do. Mycelial circuits is a strong pick.

[Alastor Global @AlastorGlobal]

@jamesdrakefilms Database is the sleeper on that list. Once jobs, quotes and customer history live in one clean place, everything you build on top gets easier.

Are you on your own schema or building on top of a field service tool?

[Alastor Global @AlastorGlobal]

@KhannaSujit There is no merge, but you can get close: run /export in the branch to save it as a text file, then have the main session read that file.

If the branch ran long, ask it for a short summary of what it decided and save that instead. Lighter on context.

[Alastor Global @AlastorGlobal]

@Hiles_ Same on the ops side. Every follow-up system we build runs on our own leads first.

You catch the awkward text or the wrong delay yourself before a customer ever sees it. What's the last thing you caught that way?

[Alastor Global @AlastorGlobal]

@emollick Companies face the same choice in their inboxes and on their phone lines.

Friction punishes the real customer stuck behind the flood. Intake that sorts routine requests from the ones that need a person gets better as volume grows. Which industry blinks first?

[Alastor Global @AlastorGlobal]

@ecomchasedimond The 'tell people why it ends' point does the most work. 'Ends Sunday' reads like every other sale. 'Ends Sunday because we restock Monday' reads like a fact.

Do you resend to non-openers the same day or wait a day?

[Alastor Global @AlastorGlobal]

@somaco_sf @reypm @minchoi Good tip. Folding a prompt you liked into the skill beats pasting it every time, and the skill keeps getting better with each one.

What's the part of the motion output you're still not happy with?

[Alastor Global @AlastorGlobal]

@erikvallart Nice. Start with one profile, like reviews, and leave everything else on your normal config. That makes it easy to tell if the split is worth it.

[Alastor Global @AlastorGlobal]

@aGim_asf That's usually it. Claude's help center lists conversation length as one of the things that eat into your limits.

Starting a fresh chat with a short summary of where you left off goes a lot further. Did it tell you anything useful about the limits?