All activity
Mario Wuleft a comment
Hey PH! 👋 I’m the maker of AgentLint. I’ve been obsessed with how AI agents "read" our code. I noticed that even the best models like Claude 3.5 or GPT-4 fail when the repo structure is noisy or lacks clear context. To find the "perfect repo" formula, I went down a deep rabbit hole: I meticulously analyzed over 200 versions of Claude Code updates to see how its internal prompting and...
AgentLintStop AI hallucinations by fixing your repo in one command.
I analyzed 200+ versions of Claude Code updates and context optimization papers to build AgentLint. It runs 33 data-backed checks to ensure your codebase is "AI-Ready"—slashing hallucinations and boosting agent reasoning by optimizing repo structure.
AgentLintStop AI hallucinations by fixing your repo in one command.
Mario Wuleft a comment
hey, been heads down on a couple claude code plugins and figured id share here one is AgentLint — basically I kept getting terrible output from AI agents and realized the problem was my repo, not the model. went down a rabbit hole reading 265 versions of Claude Code's system prompt lol. anyway turned all that into a thing that checks your repo and tells you whats broken....
🛠️ What are you building this weekend? Share your ideas 🧠 Get feedback 💬
Jake CrumpJoin the discussion
Mario Wustarted a discussion
AgentLint – Lint your repo for AI coding agents
ai coding agents were driving me crazy. same mistakes over and over, switching models and rewriting prompts didn't help much. so I flipped the question — if I can't fix the model, maybe the problem is my repo? to figure this out I dug into Claude Code's internals, went through 265 versions of its system prompt to see how it evolved, read a bunch of papers on instruction-following, and tore...