Home / Plugins / agnix

agnix

agent-sh/agnixPlugin

Lint agent configurations before they silently fail. 414 validation rules across Claude Code, Codex CLI, OpenCode, Cursor, GitHub Copilot, Gemini CLI, Cline, Windsurf, Roo Code, Amp, and Kiro - validates CLAUDE.md, AGENTS.md, SKILL.md, hooks.json, MCP server configs, and plugin manifests. Auto-fix included for safe issues; SARIF output for GitHub Code Scanning. Distributed as CLI (npm + Cargo), official GitHub Action (`agent-sh/agnix`), and IDE extensions for VS Code, JetBrains, Neovim, and Zed. Rules sourced from official specs, academic research on agent prompt design, and real-world failure patterns from production deployments. Mentioned in awesome-claude-code.

Scanned · 4 to knowPluginSource: Anthropic community marketplace
468 stars +6 this week Updated today License Apache-2.0
72popular

Why this score

Stars19/35
Usage (forks)7/15
Upkeep25/25
License15/15
Owner history6/10

Popularity score: 72/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 22, 2026 at commit c9e47613dc1d, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.

What its code does:

Web addresses in its code:

These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet. See everything for GitHub.