Hey! 👋 If you came here from the video, you’re in the right place. Everything you need to build this automation is in the document below, including the steps, prompts, and formulas. Click here: https://docs.google.com/document/d/1NiLtQk9W-FBSXJxoAH1xZ5Re7yn9i_ga/edit?usp=sharing&ouid=118174864514141048273&rtpof=true&sd=true How to use it: 1. Download the guide below 👇 2. Follow the steps in Make.com, one at a time 3. Replace “your email” with your own Gmail address 4. Test it a few times before you turn on the schedule Haven’t watched the video yet? No worries. Watch it first, then come back and build along: https://youtu.be/u3h1leMkJLM Stuck on a step? Just comment below and I’ll help you out. 🙌

Claude Mods let you change how Claude Code works. You don't need to code. Just paste a prompt below into Claude Code and it builds the mod for you. Before you start - Update Claude Code (you need version 2.1.287 or later). Check with: claude --version - Type /plugin to see your mods. - If something breaks, start with: claude --safe-mode Quick warning: mods run with the same access as Claude Code itself, so only install mods from people you trust. --- Prompts 1. /record (hides private details when you screen share) Build me a mod with a /record command that toggles recording mode. While it is on, replace any email address, phone number, API key or money amount with a placeholder before it is drawn on screen. Keep the real values in the conversation so you still work correctly. And /record off returns to normal. 2. Limits meter (never get surprised by your 5 hour window) Build me a mod that shows a small status row with how full my context is, how long until the prompt cache expires, and how much of my 5 hour and weekly limits I have used. Warn me before the cache goes cold. 3. Model selector (cheap model for easy steps, strong model for real work) Build me a mod that sends routine steps to a cheaper model and keeps the strong one for real work. Reading files, searching and summarizing go to the cheap model. Anything that writes code or makes a decision stays on the main model. Show me in the corner how many steps went to each so I can analyze it. --- 3 MORE TO TRY 4. Git branch above your prompt (easy first mod) Make a mod that shows the current git branch above the prompt box and updates when I switch branches. 5. Block risky commands (a safety net) Make a mod that blocks risky shell commands like rm -rf, force pushes and dropping database tables. When it blocks one, show me a short message saying what was blocked and why. 6. Hide secrets from Claude Make a mod that finds API keys, tokens and passwords in tool output and replaces them with [HIDDEN] before Claude reads them.

New video is up, and this one is the foundation. If you are starting out with Claude, this is the video for you. 19 minutes, and it covers the setup nobody really walks you through: models and thinking mode, memory, projects and knowledge base, skills, connectors and plugins. Here is why it matters. Everything we build from here sits on top of this. The next videos go into advanced workflows, real agents and automations running inside a business, and they all assume you already know how projects, skills and connectors work in Claude. The base is Claude. So do not skip this one, otherwise the advanced videos will feel like catching up. Get this right and the rest gets easy, fast. Chapters if you want to jump straight in: 00:00 Intro 01:17 Claude Models & Thinking Mode 03:22 Claude Memory & Importing Context 05:16 Projects & Knowledge Base 08:12 Claude Skills 13:45 Connectors & Workspace Apps 16:18 Plugins 17:25 Key Takeaways & Next Steps Watch it, then comment below with the one task you want automated first. I am picking the next builds from what you post here.