agent-sh/agnix

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.

What it solves

agnix prevents AI agent configurations from failing silently. Many AI tools (like Claude Code, Cursor, and Copilot) rely on specific configuration files (e.g., CLAUDE.md, .cursorrules) to define skills and instructions. If these files contain syntax errors or poor patterns, the AI agent may ignore the instructions entirely or produce suboptimal results without notifying the user.

How it works

It acts as a linter for agent configurations, using a library of 455 rules derived from official specifications and research. It scans specific config files across various AI tool stacks and flags errors or warnings. The tool provides an auto-fix feature to automatically correct common mistakes and integrates directly into development workflows via a CLI, GitHub Actions, and editor extensions.

Who it’s for

Developers who use AI coding assistants and agents (such as Claude Code, Cursor, Copilot, Cline, or Gemini CLI) and want to ensure their custom instructions and skill definitions are correctly implemented and active.

Highlights

  • Broad Tool Support: Validates configurations for Claude Code, Cursor, GitHub Copilot, MCP, Gemini CLI, and more.
  • Auto-fix Capabilities: Can automatically apply safe or unsafe fixes to broken configurations.
  • Multi-platform Integration: Available as a CLI (npm, Homebrew, pip, Cargo), a GitHub Action, and extensions for VS Code, JetBrains, Neovim, and Zed.
  • Extensive Rule Set: Includes 455 rules to catch everything from invalid naming conventions to generic, ineffective instructions.

Related

  • Project
    doccker/cc-use-exp

    A maintainable configuration system that synchronizes coding rules, skills, and workflows across multiple AI coding assistants like Claude Code, Cursor, and Gemini CLI.

  • Project
    jbarbier/CLAUDE.md

    A set of opinionated instructions and a workflow contract for AI coding agents to ensure high-quality, predictable code and professional communication.

  • Project
    caliber-ai-org/ai-setup

    A tool that automatically generates and maintains AI agent context files to prevent hallucinations and keep AI coding assistants in sync with codebase changes.

  • Project
    dyoshikawa/rulesync

    Rulesync is a Node.js CLI that centralises AI‑assistant configuration. You write unified `.rulesync/` rule files and the tool can generate, import, export, or convert native config files for dozens of AI coding tools (Claude, Copilot, Cursor, etc.). Installation is via npm, Homebrew, or a single‑binary script. Features include selective generation, broad tool support, deprecation handling, and a programmatic API. MIT‑licensed.

  • Project
    affaan-m/agentshield

    A security auditor for AI agent configurations that scans Claude Code setups for secrets, permission misconfigurations, and prompt injection vectors.