I just found this prompt while doom scrolling instagram: "Help me set up permissions using /permissions. I want to pre-approve three things: Safe commands so Claude doesn't stop to ask every time: Is, cd, mv, cp, cat, and open Reading files in my working folder without asking Fetching safe webpages without asking Walk me through each one." I ran it in claude code (using vs code, but I don't think it matters). It just did it and wrote to the ~/.claude/settings.json file, so that claude can now continue to build less interuptions! I hope I didn't just unleash a beast or anything....

A few months ago I was building Lead Scout — a personal AI pipeline that finds companies adopting AI, scores them for fit, tracks down a decision-maker, and drafts me a personalised cold email. All automated. All local. No monthly SaaS bill. It worked. Kind of. The results were noisy, the email drafts ran too long, and I had a nagging feeling that something was architecturally off but I couldn’t put my finger on what. I was patching symptoms instead of diagnosing the system. Then I came across a post from someone in this community — I genuinely cannot remember your name and it’s driving me mad — but they were using Norse Gods as AI agent roles to review and improve their project. Thor for raw power, Odin for wisdom, that kind of thing. Whoever you are: thank you. That post changed how I think about working with AI. If anyone knows who I’m talking about, please tag them. I owe them a coffee. The idea clicked something in my brain. What if instead of asking one Claude instance to do everything, I gave each review role its own identity, its own domain, and its own rules? So I built The Council. Three agents. Egyptian theme, because why not. Ra — The Architect Ra sees the whole system from above. He doesn’t touch code. He thinks in pipelines, sequences, tool choices, and strategic gaps. Before any major change, Ra reviews the architecture and asks: are we building the right thing, in the right way, for the right reasons? Ra runs twice per session — same prompt, two separate Claude instances — because he often approaches the same problem from different angles. Concerns that appear in both sessions are high priority. Concerns that appear in only one are still worth investigating. Anubis — The Surgeon Anubis goes stage by stage through the actual code. File names. Function names. Exact failure conditions. He doesn’t guess and he doesn’t generalise. If Ra says “the scoring stage feels fragile,” Anubis finds exactly which line is fragile and exactly why. He only reports what he can point to specifically. He weighs everything on the scales — nothing passes without evidence.