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.
This repository also configures its own agents. See what cladding tells them →
Plugin Claude Code
Bundles 1 command, 6 agents, 5 hooks · 429 tokens together
Reference implementation of the Ironclad standard — multi-agent dev harness for Claude Code.
Plugin Gemini CLI
Reference implementation of the Ironclad standard — multi-agent dev harness for Gemini CLI. Exposes spec validation, drift detection, 15 Iron Law stages, and 5 agent personas as custom commands + an auto-launched MCP server.