This is a structured way to make any repo work reliably with autonomous agents. It scaffolds the artifacts OpenAI recommends in their Harness Engineering guide: AGENTS.md and PLANS.md for context, deterministic Makefile commands so agents can test and lint without surprises, architecture boundaries to prevent overstep, and observability hooks from the start. You get three profiles depending on how much discipline you want baked in. The audit command treats missing practices as blocking, which is the right default. If you're building something agents will touch repeatedly, this gives you the guard rails and documentation structure to keep runs from diverging into chaos.
npx skills add https://github.com/broomva/harness-engineering-skill --skill harness-engineering-playbook