In this season of life, it's challenging to find time to do full coding stretches and manage new products/businesses, so I've started to build and release concepts, ideas and prototypes in a new public repo. I've taken the ICM workflows to heart and built my own variants. I'm also using and building workflows as public projects that others can use as a starter for painful problems I've researched in the marketplace. Love to get feedback from this community - both on the idea of building and sharing this publicly, and the projects that are shared, if they're genuinely useful. The primary thought is I can build and share these in the open rather than hold on to them and do nothing with them. And at the same time, I could build an email newsletter list for the future when I do re-enter the marketplace. I've included some links in the comments below.👇

Every day for the last few months, I have enjoyed seeing one or two new members using my AI powered poker training app. Last night it hit 30 members! For anyone in the community that wonders if your idea could be real, it can be and you should go for it! ✌️ If you haven’t checked it out, here is the link. https://allintrainer.com

Greetings everyone: Just passing by to talk about my first client interaction. It was not as expected, but quite a learning experience. First of all, I jumped right into working without talking about price (first error) and then, i solved a big problem for my client: his webpage had a lot of trouble, and he is an AI enthuciast and tryed to fix it himself. I did an excelent job and manage to get score 100 on SEO that was his first issue. Also was built on wordpress and had a lot of pluggins and the webpage was not responsive. In the way i found that he had a italian hacker (at least the IP said so) and belive it or not, the hacker made a admin acount and noone noticed for a whole year. Also he added malicious malware on the base. I rebuild the website. It took me about 5 days of work and charged about 600 bucks for all. I noticed he had payed a chatbot, a good one chilean startup and payed 200 bucks for it monthly. The website sold almost 0 on the last 3 months. He also hired a digital marketing agency for 1000 bucks for managing google ads and meta ads. I also noticed they were doing a horrible job. I proposed him charging him half of the price they were charging to make an Agentic solution for it, a good one. Also on the way i made my own chatbot using LangGraph and Gemini, even offered product with a picture or audio! Im proud of it. The thing is even thou i demostrated my skills with AI and my speed, he offered me crums: only a comition payed when the website started selling (almost 100% of the sales are non web) and ofered me very very little money for % of sales. He sent me the offer today (17 days since i started working with him). I spoke with him and he was sure it was a good offer and also asured me there were no other way. They had no intentions on making me an AI Partner. I just sent him a backoffer refusing the sales % and offering good AI products that are still a win win for both of us. I feel kinda relieved because at some point i considered the offer. I spoke with my good pal Claude and review everything in detail and made a detailed auditory about the digital marketing agency.

A recruiter contacted me on LinkedIn on Wednesday. CEO of a crypto startup, $125/hr advisory role, review our product via GitHub repo as the first interview step. The social engineering was top-notch, polished profile with 500+ connections, days of back and forth DMs, the cracks only appeared in hindsight. Friday, I got access to the repo, which felt like a win. With a healthy amount of skepticism, I reviewed the repo with Claude. The codebase looked professional and complete, the README was well structured, and the .json files where malware would normally be hidden came back clean. The payload was buried well enough that Claude and I missed it. Luckily, I decided to enjoy my Friday night and not clone the repo. This is the main reason I want to share my story here: many of us are starting new businesses, and when someone offers you a paid role that seems like the perfect fit, your judgment becomes clouded. I know mine did.Having had more time to think, the inconsistencies started to surface. Lying in bed around midnight on Saturday, the eureka moment happened. This was definitely an elaborate scam. I stayed up all night digging through the repo and gathering evidence to file reports. Here’s what I found: The repo contained a fully operational malware delivery chain: - .vscode/tasks.json configured with runOn: folderOpen — silent code execution the moment you open the folder in VS Code, zero prompt. - .githooks/post-checkout buried under 40 lines of decoy comments, downloading and executing a remote payload from a Vercel server across Mac, Linux, and Windows simultaneously, all output suppressed. - Private key social engineering via the .env.local README instruction, a backup vector in case the malware delivery fails or gets caught  - This is a complex attack chain designed to pass pre-clone inspection. Once you clone it, you’re cooked. I stayed up all night gathering evidence and filing reports: Vercel - both domains, GitHub - account + repo, LinkedIn profile, Basescan wallet flagged, Neynar/Farcaster. Then the big guns: RCMP/CAFC and FBI IC3. But then I started thinking, what tools should I have used to protect myself in this situation?

Not sure if there is a right answer here or if it's a preference thing but my question is do ya'll compact a session or take that as a hint to wrap up current work and start a new session? I'm using VS Code and when I see the auto compact about to set off, I ask claude to update the respective .md files in the workspace to wrap up the session. Is that less efficient than just compacting? I suppose my thought process was if the .mds inside the workspace are lean enough then a new session would be more token efficient than compacting.