AgentRuleLint

Audit coding agent instruction files for consistency to prevent behavior drift

Problem

Developers find that as projects grow, global prompts and instruction files (AGENTS.md, .cursorrules, etc.) for AI coding agents become bloated and self-contradictory. For example, one rule says 'always format after coding' while another forbids modifications before commit. This leads to unpredictable agent behavior and degrading code quality. Users complain that global prompts have limited effect and cannot enforce compliance even after repeated trimming.

Solution

A local CLI tool that scans agent instruction files (including nested ones), parses rules, detects logical contradictions, duplications, outdated or conflicting requirements, and generates a readable report. It also tracks changes over time to alert on rule drift, helping developers maintain a clear, consistent behavioral contract for agents.

Users

Individual developers or small teams using AI coding agents daily, with medium-to-large projects and multiple agent config files.

MVP

Parse common instruction file formats (Markdown lists, YAML); detect basic rule conflicts (negation vs. affirmation, temporal contradictions); output colored terminal report; offer --fix suggestions (advisory only); allow ignoring specific rules.

Revenue

Open-source core with paid advanced features (team-shared rule libraries, CI integration, custom rule packs), or a one-time purchase desktop app.

Why now

AI coding agents are rapidly adopted, but instruction management is still wild west; developers widely face prompt bloat and rule conflicts, and few tools address this. Indie developers can quickly enter this niche.