agnix
AI agent config linter and LSP — validates Claude Code skills, hooks, and MCP configs with autofixes
Agnix is a linter and Language Server Protocol (LSP) tool for AI coding assistant configurations, ensuring Claude Code skills, hooks, and MCP server definitions are correctly formatted before deployment. It provides 399 rules sourced from official specifications and real-world breakage patterns, offering detailed diagnostics and automatic fixes for common issues across various agent tools. Integrates with major IDEs like VS Code, JetBrains, and Neovim, and includes a GitHub Action for CI/CD workflows.
- Validates Claude Code skills, hooks, and MCP configs
- Enforces 399 rules from official specs and common patterns
- Provides automatic fixes for identified configuration errors
- Integrates as an LSP into VS Code, JetBrains, Neovim, and Zed
- Offers a GitHub Action for CI/CD pipeline validation
README
View on GitHub ↗
agnix
Lint agent configurations before they break your workflow
Catch broken agent configs before your AI tools silently ignore them.
399 rules across Claude Code, Codex CLI, OpenCode, Cursor, Copilot, and more -
validating CLAUDE.md, SKILL.md, hooks, MCP configs, and other agent files.
Auto-fix | GitHub Action | VS Code + JetBrains + Neovim + Zed
New rules and tool support ship constantly. Follow for real-time updates:
Why agnix?
Your skills don't trigger. Vercel's research found skills invoke at 0% without correct syntax. One wrong field and your skill is invisible.
"Almost right" is the worst outcome. 66% of developers cite it as their biggest AI frustration. Misconfigured agents produce exactly this.
Multi-tool stacks fail silently. Cursor + Claude Code + Copilot each want different formats. A config that works in one tool breaks in another.
Bad patterns get amplified. AI assistants don't ignore wrong configs - they learn from them.
agnix validates all of it - 399 rules sourced from official specs, academic research, and real-world breakage patterns. Auto-fix included.
Want to try it first? Open the playground - paste any agent config, see diagnostics instantly. No install, runs in your browser.
Quick Start
$ npx agnix .
Validating: .
CLAUDE.md:15:1 warning: Generic instruction 'Be helpful and accurate' [fixable]
help: Remove generic instructions. Claude already knows this.
.claude/skills/review/SKILL.md:3:1 error: Invalid name 'Review-Code' [fixable]
help: Use lowercase letters and hyphens only (e.g., 'code-review')
Found 1 error, 1 warning
2 issues are automatically fixable
hint: Run with --fix, --fix-safe, or --fix-unsafe to apply fixes
https://github.com/user-attachments/assets/72d5fe7c-476f-46ea-be64-5785cf6d5600
Install
# npm (recommended, all platforms)
npm install -g agnix
# Homebrew (macOS/Linux)
brew tap agent-sh/agnix && brew install agnix
# Cargo
cargo install agnix-cli
Pre-built binaries | All install options
Editor Extensions
| Editor | Install |
|---|---|
| VS Code | VS Code Marketplace |
| JetBrains | JetBrains Marketplace |
| Neovim | { "agent-sh/agnix", config = function() require("agnix").setup() end } |
| Zed | Search "agnix" in Extensions |
GitHub Action
- name: Validate agent configs
uses: agent-sh/agnix@v0
with:
target: 'claude-code'
Usage
agnix . # Validate current directory
agnix --fix . # Apply HIGH and MEDIUM confidence fixes
agnix --fix-safe . # Apply only HIGH confidence fixes
agnix --fix-unsafe . # Apply all fixes, including LOW confidence
agnix --dry-run --show-fixes . # Preview fixes with inline diff output
agnix --strict . # Strict mode (warnings = errors)
agnix --target claude-code . # Legacy target preset (primarily affects CC-* rules)
agnix --target kiro . # Legacy target preset (use tools = [...] for tool-only filtering)
Full CLI reference | Full rules reference
Supported Tools
| Tool | Rules | Count | Config Files |
|---|---|---|---|
| Agent Skills | AS-*, CC-SK-* | 31 | SKILL.md |
| Claude Code | CC-* | 53 | CLAUDE.md, hooks, agents, plugins |
| GitHub Copilot | COP-* | 6 | .github/copilot-instructions.md, .github/instructions/*.instructions.md |
| Cursor | CUR-* | 16 | .cursor/rules/*.mdc, .cursorrules, .cursor/hooks.json, .cursor/agents/**/*.md, .cursor/environment.json |
| Kiro | KIRO-*, KR-SK-*, KR-AG-*, KR-HK-*, KR-PW-*, KR-MCP-* | 51 | .kiro/steering/**/*.md, .kiro/skills/**/SKILL.md, .kiro/agents/*.json, .kiro/hooks/*.kiro.hook, .kiro/settings/mcp.json, .kiro/powers/*/POWER.md |
| MCP | MCP-* | 12 | *.mcp.json |
| AGENTS.md | AGM-*, XP-* | 13 | AGENTS.md, AGENTS.local.md, AGENTS.override.md |
| Cline | CLN-* | 4 | .clinerules, .clinerules/*.md, .clinerules/*.txt |
| Gemini CLI | GM-* | 9 | GEMINI.md, GEMINI.local.md, .gemini/settings.json (hooks), gemini-extension.json (extensions), .geminiignore |
Architecture
Rust workspace crates:
agnix-rules- rule metadata generated fromknowledge-base/rules.jsonagnix-core- shared validation engine libraryagnix-cli- command-line interface binaryagnix-lsp- language server binaryagnix-mcp- MCP server binaryagnix-wasm- WebAssembly bindings for browser/runtime integrations
Contributing
Contributions welcome. See CONTRIBUTING.md for the development guide.
Report a bug | Request a rule | Good first issues
License
MIT OR Apache-2.0
Star this repo to help other developers find agnix.
Similar other
MiroFish
Swarm intelligence engine for future prediction — simulates multi-agent interactions to deduce outcomes
paperclip
AI agent orchestration server for autonomous companies — manages teams of bots, goals, budgets, and governance
learn-claude-code
Agent harness engineering tutorial — build the environment and tools for real LLM agents, inspired by Claude Code
LightRAG
Lightweight RAG framework — builds simple, fast, and scalable retrieval-augmented generation systems for LLMs
