Lint rules for your AI agent's discipline, not its code

Automated quality checks that nudge AI coding agents toward better habits

Finds the claims in your CLAUDE.md / AGENTS.md / skills that your code no longer supports. Zero-config, no API key.

Copy/paste detector for source code. 220+ languages, Rust engine, SARIF/HTML/badge reporters, GitHub Action, MCP server for AI agents.

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.