I literally maxed out my subscription researching and putting all the best research into the skill for you guys... /loop + /goal skill for Claude Code that helps you turn a project idea into a fully planned execution prompt your agents can run with overnight. Repo: https://github.com/jbrazy480/loop-maker.git The goal was simple: Most people don’t fail because Claude is weak. They fail because the initial prompt is messy, the goal is unclear, and the agent has no real execution loop. This skill helps fix that by forcing better planning, cleaner constraints, stronger task decomposition, and a tighter agent workflow before execution starts. I built this using the best /loop and /goal strategies I could find, plus what I’ve learned from studying the Fable-style planning workflow. I genuinely maxed out my subscription building and testing this, so I figured I’d share it here for free. If this is useful, I’ll keep dropping more resources for the community.

I gave Claude Fable a single goal prompt: build me a complete company from scratch, starting with nothing but the open internet. A few hours later I had a real product, a landing page, two launch videos, a founder video, a business plan, and market research, all built by hundreds of subagents that Fable planned, delegated, and reviewed. In this video I walk through everything it produced and break down the exact prompt that made it happen.

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊

I switched Claude Code over to GLM 5.2 and ran it all day. It's a 756 billion parameter open source model you can route straight into the Claude Code harness for about five times cheaper than Opus, and for most of my knowledge work it held up fine. In this one I show you what it can build, where it beats Opus and where it doesn't, and exactly how to set it up so you can switch between models per project. Here's the config I use. Drop this into your .claude/settings.local.json and swap in your own Z.ai key: "env": { "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic", "ANTHROPIC_AUTH_TOKEN": "your-z-ai-api-key-here", "ANTHROPIC_API_KEY": "", "API_TIMEOUT_MS": "3000000", "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-5.2", "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-5.2", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-5.2", "ANTHROPIC_SMALL_FAST_MODEL": "glm-5.2", "CLAUDE_CODE_SUBAGENT_MODEL": "glm-5.2" }