Harness Engineering

Patterns for making codebases legible to coding agents and scaling engineering throughput through agent delegation. Full source transcripts are in references/.

The goal is a codebase where agents autonomously produce acceptable code without human intervention.

Agentic Legibility Scorecard

Score a repository across these seven metrics (each 0-3, max 21):

1. Bootstrap Self-Sufficiency

Can an agent clone the repo and get a working environment with zero external knowledge? Look for: setup scripts, dependency declarations, env templates, seed data.