0xmariowu

0xmariowu / AgentLint

Public

Lint your repo for AI agent compatibility.

agentlint.app agentic agents-md ai-agent ai-friendly ai-tools
10
0
100% credibility
Found Apr 07, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

AgentLint scans code projects to score and improve their structure, instructions, build processes, safety, and continuity specifically for AI coding agents like Claude Code.

How It Works

1
📖 Discover AgentLint

You hear about a handy checker that helps make your projects easier for AI helpers to understand and work with.

2
🛠️ Add the checker

With one easy step on your computer, you bring the tool into your setup so it's ready to use.

3
💻 Start AI session

You open a new chat with your AI coding buddy in your favorite project folder.

4
✨ Get your score

You share a quick note with the AI, and it instantly shows colorful bars rating your project across easy-to-find info, clear rules, build steps, safety, and session flow.

5
🔧 Apply fixes

You pick from guided or automatic suggestions, like adding key files or cleaning up rules, and the tool makes changes safely.

🎉 Project shines

Your score jumps up, you save a beautiful report comparing before and after, and now your AI helper works smoothly without confusion or mistakes.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is AgentLint?

AgentLint scans your Git repository for AI agent compatibility, scoring it across findability, instructions, workability, safety, and continuity with 33 data-backed checks. It generates lint reports like an Android lint report or Sonar lint report, but tailored for AI tools—pinpointing issues like broken references in CLAUDE.md or unpinned GitHub Actions that trip up agents. Install via npm, run `/al` in Claude Code for scores, HTML reports, and guided fix plans.

Why is it gaining traction?

Unlike golangci-lint GitHub actions or Ansible lint repo tools that focus on code style, AgentLint targets AI-specific pitfalls, drawing from 265 Anthropic prompt versions and academic papers on agent behavior. Developers hook into it via lint GitHub workflow integration or as a standalone agent linter, getting prioritized fixes like adding HANDOFF.md or pinning actions—saving tokens and reducing session resets. The Claude Code plugin makes it dead simple, with before/after reports showing real gains.

Who should use this?

AI-heavy teams building with Claude Code or Cursor, especially in monorepos where agents lose context across sessions. Frontend devs linting workflows for agent-driven PRs, or backend folks ensuring safe CI triggers without supply chain risks. Ideal if you're tired of repeating instructions or debugging why agents ignore your rules.

Verdict

Worth trying for Claude Code users—solid docs and evidence-based checks punch above its 10 stars and 1.0% credibility score. Still early; test on a side repo before production lint GitHub actions.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.