Back to directory

agnix

A linter and language server for AI agent configuration files, validating CLAUDE.md, AGENTS.md, SKILL.md, hooks, and MCP configs against hundreds of rules, with autofixes and editor integrations.

agnix

agnix validates configuration files used by AI coding assistants, catching mistakes that would otherwise cause a tool to silently ignore a skill, hook, or MCP server. It applies hundreds of rules sourced from official specs and observed failure patterns across Claude Code, Codex CLI, OpenCode, Cursor, GitHub Copilot, and other tools, checking files such as CLAUDE.md, SKILL.md, hooks, and MCP configuration, with automatic fixes for many violations.

It installs through npm, Homebrew, pip, or Cargo, and is written in Rust. Extensions bring the same checks into VS Code, JetBrains IDEs, Neovim, and Zed, and a GitHub Action can validate agent configs in CI. A browser-based playground lets users paste a config and see diagnostics without installing anything.

The rules are grouped by tool, for example a set specific to Claude Code covering CLAUDE.md, hooks, agents, and plugins, and another for Agent Skills covering SKILL.md.

More in Code quality

See all 94
  • Critic

    critic.run

    A code-change viewer, backed by Y Combinator, built for reviewing work written by coding agents, presenting a plain-language narrative of each change alongside the diff and a running conversation with the agent.

  • GitIntel

    hoangsonww.github.io

    An MCP server that computes git repository analytics such as hotspots, churn, temporal coupling, knowledge maps and risk scoring entirely from local commit history, for AI coding agents like Claude Code and Codex.

  • Axint

    axint.ai

    A verification layer for AI coding agents working on Apple projects: it runs real Xcode builds and tests against the Swift an agent wrote, reconciles static analysis findings against that evidence, and returns a signed proof with the exact repairs still needed.