For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in before it writes, and the result is verified against your spec after, so those three are earned, not assumed. First L4 implementation of the Ironclad standard.
Reference implementation of the Ironclad standard — multi-agent dev harness for OpenAI Codex CLI / IDE / cloud. Exposes spec validation, drift detection, the Iron Law stage runner, and 5 agent personas as Codex skills + an auto-launched MCP server.