avifenesh

avifenesh / agnix

Public

The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.

agent ai ai-agents ai-coding-assistant claude
66
4
100% credibility
Found Feb 12, 2026 at 25 stars 3x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

Agnix validates AI agent configuration files for tools like Claude, Cursor, and Copilot to catch syntax errors and best practice violations before they silently break your workflow.

How It Works

1
🔍 Discover agnix

You hear about agnix from a blog post or editor marketplace while troubleshooting why your AI assistant ignores your custom instructions.

2
📦 Get it set up

Install the helper tool or add it to your favorite code editor with one click—no complicated steps needed.

3
📁 Check your project

Point it at your project folder and let it scan your AI setup files for common mistakes.

4
⚠️ Spot the issues

It highlights exactly what's wrong—like bad skill names or missing details—with friendly explanations and one-click fixes.

5
🔧 Fix automatically

Apply the suggested fixes to make your AI instructions work perfectly across different tools.

6
🔄 Add to your routine

Connect it to your editor for real-time checks or your team's review process so problems never sneak in.

✅ Perfect AI setup

Your AI agents now respond exactly as intended, saving hours of frustration and debugging.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 25 to 66 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 agnix?

Agnix is a Rust-based linter and LSP for AI coding assistants, validating configs like CLAUDE.md, AGENTS.md, SKILL.md, hooks, and MCP.json to catch silent failures before they break workflows. It scans for 156 rules across Claude Code, Cursor, Copilot, and more, offering autofixes via CLI (`agnix --fix .`), GitHub Actions, and plugins for VS Code, JetBrains, Neovim, Zed. Solves the agnix ai pain where skills invoke at 0% due to syntax errors, as seen in Vercel evals.

Why is it gaining traction?

Unlike generic YAML/JSON validators, agnix targets AI-specific breakage patterns from official specs and real-world surveys—66% of devs frustrated by "almost right" agents.md. Autofixes handle kebab-case names or XML balance, while multi-tool support prevents Cursor configs breaking in Claude. GitHub Action integration fixes github missing access token issues in hooks, making CI seamless for assistants.

Who should use this?

AI workflow engineers stacking Claude Code with Cursor or Copilot, where CLAUDE.md conflicts with AGENTS.md. Open-source maintainers validating skills in repos to avoid github missing contributions from ignored tools. MCP builders ensuring JSON schemas don't silently fail in production agents.

Verdict

Grab the VS Code extension if you're deep in agnix ai setups—docs shine, coverage is solid. But at 24 stars and 1.0% credibility, it's early; test in non-critical flows until adoption grows.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.