RuleLint — Coding Agent Rule Compliance Auditor

Automatically check whether AI coding agents follow the CLAUDE.md rules in your repo

Problem

Teams increasingly write CLAUDE.md / AGENTS.md rule files for coding agents (naming conventions, forbidden paths, approved libraries), but agents quietly violate them—touching files they shouldn't, importing banned packages—and humans only catch it during code review. No tool specifically audits rule compliance.

Solution

Parse the rule file, turn natural-language rules into executable checks, scan each agent commit's diff, and report which rules were broken and where, optionally commenting on the PR.

Users

Engineering teams of 2–20 using Claude Code, Cursor, Codex or similar coding agents.

MVP

Parse CLAUDE.md-style rule files into a structured checklist; match rules against git diffs at file and line level; CLI outputs violations with non-zero exit codes; GitHub Action comments on PRs; ship 3–5 common rule templates (forbidden paths, naming, dependency allowlist).

Revenue

Open-source CLI plus a cloud team plan (private rule library, history, CI integration) at $9–19 per user per month.

Why now

CLAUDE.md-style rule files are becoming standard in the coding-agent era, yet rule enforcement is an empty niche—small enough for an indie dev to build with LLM plus static checks.