An instruction layer for AI coding agent

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.