A developer on GitHub just built a full development methodology for AI coding agents and it has 91,000 stars. It's called Superpowers, and it completely changes how your AI agent writes code. The backstory is what makes this wild. Jesse Vincent created Request Tracker in 1994. It became the most widely used open-source ticket tracking system on Earth. He ran the Perl programming language for three years. He co-founded Keyboardio and shipped ergonomic keyboards to 78 countries. He co-founded VaccinateCA during COVID and helped millions find vaccines. Every one of those projects solved the same problem: helping people organize complex work they can't hold in their heads. Five months ago he released Superpowers, a set of markdown skill files that plug into Claude Code, Codex, or Cursor. The entire value is in the constraints. Before the agent writes a single line, it stops and asks what you're building. It writes a spec in chunks small enough to read. It breaks implementation into 2-5 minute tasks with exact file paths. It enforces test-driven development so strictly that it deletes code written before tests exist. 91,000 stars in five months. For a repo that is mostly markdown files telling your AI agent to slow down. That growth tells you something uncomfortable. The bottleneck in AI-assisted development right now is not model capability. The models are smart enough. The problem is they have zero discipline. They guess at specs, skip tests, and produce code you spend the next hour babysitting. A guy who spent 30 years building systems for how humans organize work just built the system for how AI agents organize work. The career arc makes perfect sense in retrospect. Resources: 1. Superpowers repo: https://lnkd.in/gN6NXzrM 2. My Claude Code OS: https://lnkd.in/gsH9RSfJ 3. Claude Code tutorial: https://lnkd.in/eXNvwvWw The teams that figure out AI agent discipline first will look like they have a two-year head start. The teams that let agents freewheel will spend that time cleaning up. Follow Aakash Gupta for daily AI + PM insights.

705 reactions · 37 comments