Make Claude Code and other coding agents good at your codebase: a harness built from your code (CLAUDE.md, flow guides, scripts, tests), measured before and after.
Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with one command.
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.
