Structural governance for AI coding agents. 33 agents, 23 commands, 32 skills, 8 MCP governance tools, and 7 hooks that enforce a core rule: verifier.agent != task.agent — no agent grades its own homework. Adds health scoring (A-F grades across 8 dimensions), live drift detection, quality gates, cross-agent verification, and shared memory to any Claude Code project. Optional Rust orchestrator (4MB binary) for file locking and multi-tool coordination across Claude Code, Codex CLI, and Gemini CLI. 4,579 tests across the trilogy. Built from 23 years of global program delivery. MIT licensed.