Summary
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.
Install to Claude Code
npx -y skills add broomva/harness-engineering-skill --skill harness-engineering-playbook --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
