Skip to content
Back to search

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.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/agent-sh/agnix with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/agent-sh/agnix'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/agent-sh--agnix/badge.svg)](/listings/agent-sh--agnix)

HTML

<a href="/listings/agent-sh--agnix"><img src="/api/listings/agent-sh--agnix/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

$ 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

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 220 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="editors/vscode/icon.png" alt="agnix" width="128">
  3. <h1>agnix</h1>
  4. <p><strong>Lint agent configurations before they break your workflow</strong></p>
  5. <p>
  6. <a href="https://www.npmjs.com/package/agnix"><img src="https://img.shields.io/npm/v/agnix.svg?color=3C873A" alt="npm"></a>
  7. <a href="https://crates.io/crates/agnix-cli"><img src="https://img.shields.io/crates/v/agnix-cli.svg?color=E57324" alt="Crates.io"></a>
  8. <a href="https://github.com/agent-sh/agnix/releases"><img src="https://img.shields.io/github/v/release/agent-sh/agnix?color=0A7E8C" alt="Release"></a>
  9. <a href="https://github.com/agent-sh/agnix/actions/workflows/ci.yml"><img src="https://github.com/agent-sh/agnix/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
  10. <a href="LICENSE-MIT"><img src="https://img.shields.io/badge/license-MIT%2FApache--2.0-64748B.svg" alt="License"></a>
  11. <a href="https://github.com/hesreallyhim/awesome-claude-code"><img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code"></a>
  12. </p>
  13. </div>
  14. > Running open models for your company? [**Tiyuvta**](https://tiyuvta.ai/services/) helps with model choice, deployment and optimization, and fine-tuning on your hardware or cloud account.
  15. <p align="center">
  16. <a href="https://github.com/sponsors/avifenesh"><img src="https://img.shields.io/badge/Sponsor-%E2%9D%A4-db61a2?style=for-the-badge&logo=githubsponsors&logoColor=white" alt="Sponsor"></a>
  17. </p>
  18. <p align="center"><b>Built and maintained with a lot of agent tokens and hours. If it saves you time, <a href="https://github.com/sponsors/avifenesh">sponsoring</a> helps keep it going.</b></p>
  19. <p align="center">Catch broken agent configs before your AI tools silently ignore them.<br>761 rules across Claude Code, Codex CLI, OpenCode, Cursor, Copilot, and more -<br>validating CLAUDE.md, SKILL.md, hooks, MCP configs, and other agent files.</p>
  20. <p align="center"><strong>Auto-fix</strong> | <strong><a href="https://github.com/marketplace/actions/agnix-ci">GitHub Action</a></strong> | <strong><a href="https://marketplace.visualstudio.com/items?itemName=avifenesh.agnix">VS Code</a> + <a href="https://plugins.jetbrains.com/plugin/30087-agnix">JetBrains</a> + <a href="https://github.com/agent-sh/agnix/tree/main/editors/neovim">Neovim</a> + <a href="https://zed.dev/extensions?query=agnix">Zed</a></strong></p>
  21. <p align="center">
  22. <a href="https://agent-sh.github.io/agnix/"><img src="https://img.shields.io/badge/Docs-Website-2563EB?style=for-the-badge" alt="Website"></a>
  23. <a href="https://agent-sh.github.io/agnix/playground"><img src="https://img.shields.io/badge/Try_it-Playground-E91E63?style=for-the-badge" alt="Playground"></a>
  24. <a href="https://dev.to/avifenesh/your-ai-agent-configs-are-probably-broken-and-you-dont-know-it-16n1"><img src="https://img.shields.io/badge/Blog-Post-0A0A0A?style=for-the-badge&logo=dev.to" alt="Blog Post"></a>
  25. </p>
  26. <p align="center"><em>New rules and tool support ship constantly. Follow for real-time updates:</em></p>
  27. <p align="center">
  28. <a href="https://x.com/avi_fenesh"><img src="https://img.shields.io/badge/Follow-@avi__fenesh-1DA1F2?style=for-the-badge&logo=x&logoColor=white" alt="Follow on X"></a>
  29. </p>
  30. ## Why agnix?
  31. **Your skills don't trigger.** Vercel's research found skills [invoke at 0%](https://vercel.com/blog/agents-md-outperforms-skills-in-our-agent-evals) without correct syntax. One wrong field and your skill is invisible.
  32. **"Almost right" is the worst outcome.** [66% of developers](https://survey.stackoverflow.co/2025/ai) cite it as their biggest AI frustration. Misconfigured agents produce exactly this.
  33. **Multi-tool stacks fail silently.** Cursor + Claude Code + Copilot each want different formats. A config that works in one tool [breaks in another](https://arnav.tech/beyond-copilot-cursor-and-claude-code-the-unbundled-coding-ai-tools-stack).
  34. **Bad patterns get amplified.** AI assistants don't ignore wrong configs - they [learn from them](https://www.augmentcode.com/guides/enterprise-coding-standards-12-rules-for-ai-ready-teams).
  35. agnix validates all of it - 761 rules sourced from official specs, academic research, and real-world breakage patterns. Auto-fix included.
  36. > **Want to try it first?** [Open the playground](https://agent-sh.github.io/agnix/playground) - paste any agent config, see diagnostics instantly. No install, runs in your browser.
  37. ## Quick Start
  38. ```console
  39. $ npx agnix .
  40. Validating: .
  41. CLAUDE.md:15:1 warning: Generic instruction 'Be helpful and accurate' [fixable]
  42. help: Remove generic instructions. Claude already knows this.
  43. .claude/skills/review/SKILL.md:3:1 error: Invalid name 'Review-Code' [fixable]
  44. help: Use lowercase letters and hyphens only (e.g., 'code-review')
  45. Found 1 error, 1 warning
  46. 2 issues are automatically fixable
  47. hint: Run with --fix, --fix-safe, or --fix-unsafe to apply fixes
  48. ```
  49. https://github.com/user-attachments/assets/72d5fe7c-476f-46ea-be64-5785cf6d5600
  50. ## Install
  51. ```bash
  52. # npm (recommended, all platforms)
  53. npm install -g agnix
  54. # Homebrew (macOS/Linux)
  55. brew tap agent-sh/agnix && brew install agnix
  56. # pip (or `uvx agnix .` to run without installing)
  57. pip install agnix
  58. # Cargo
  59. cargo install agnix-cli
  60. ```
  61. [Pre-built binaries](https://github.com/agent-sh/agnix/releases) | [All install options](https://agent-sh.github.io/agnix/docs/installation)
  62. ### Editor Extensions
  63. | Editor | Install |
  64. |--------|---------|
  65. | **VS Code** | [VS Code Marketplace](https://marketplace.visualstudio.com/items?itemName=avifenesh.agnix) |
  66. | **JetBrains** | [JetBrains Marketplace](https://plugins.jetbrains.com/plugin/30087-agnix) |
  67. | **Neovim** | `{ "agent-sh/agnix", config = function() require("agnix").setup() end }` |
  68. | **Zed** | Search "agnix" in Extensions |
  69. [Editor setup guide](https://agent-sh.github.io/agnix/docs/editor-integration)
  70. ### GitHub Action
  71. ```yaml
  72. - name: Validate agent configs
  73. uses: agent-sh/agnix@v0
  74. with:
  75. target: 'claude-code'
  76. ```
  77. ## Usage
  78. ```bash
  79. agnix . # Validate current directory
  80. agnix --fix . # Apply only safe fixes
  81. agnix --fix-safe . # Explicit safe-only fix mode
  82. agnix --fix-unsafe . # Apply all fixes, including medium and LOW confidence
  83. agnix --dry-run --show-fixes . # Preview fixes with inline diff output
  84. agnix --strict . # Strict mode (warnings = errors)
  85. agnix --format github . # GitHub Actions annotations
  86. agnix explain MCP-018 # Explain a rule and its evidence
  87. agnix --target claude-code . # Only Claude Code rules plus generic ones, like tools = ["claude-code"]
  88. agnix --target kiro . # Only Kiro rules plus generic ones, like tools = ["kiro"]
  89. ```
  90. [Full CLI reference](https://agent-sh.github.io/agnix/docs/configuration) | [Full rules reference](https://agent-sh.github.io/agnix/docs/rules)
  91. Kiro permission YAML templates at `.kiro/settings/permissions.yaml` are lintable. The actual user policy is `~/.kiro/settings/permissions.yaml`; workspace policies live outside the repository at `~/.kiro/workspace-roots/<hash>/permissions.yaml`. Lint those paths explicitly to check the active policies.
  92. ## Supported Tools
  93. Maintenance priorities:
  94. | Tier | Tools |
  95. |------|-------|
  96. | S | Claude Code, Codex CLI |
  97. | A | Kiro, OpenCode, Pi |
  98. | B | Antigravity CLI, Grok Code |
  99. | C | Muse Code, Kimi Code |
  100. | D | GitHub Copilot, Cline, Cursor, legacy Gemini CLI |
  101. Pi, Antigravity CLI and Grok Code have native static validators and automated release tracking. Muse Code and Kimi Code validation remains pending. See the [coverage and monitoring inventory](knowledge-base/RESEARCH-TRACKING.md) and [native contracts](knowledge-base/NATIVE-TOOL-CONTRACTS.md) for supported formats and qualified versions.
  102. Implemented validators:
  103. | Tool | Rules | Count | Config Files |
  104. |------|-------|-------|--------------|
  105. | [Pi](https://pi.dev) | PI-\* | 17 | .pi/settings.json, ~/.pi/agent/, models, keybindings, MCP, packages, themes and prompts |
  106. | [Antigravity CLI](https://antigravity.google/docs/getting-started?tab=cli) | AGY-\* | 18 | CLI settings, mcp_config.json, hooks, plugins, rules, registries and agents |
  107. | [Grok Code](https://docs.x.ai/build/cli/reference) | GRK-\* | 20 | .grok/config.toml, sandbox, requirements, roles, personas, hooks, plugins, LSP, agents and skills |
  108. | [Agent Skills](https://agentskills.io) | AS-\*, XP-SK-\* | 26 | SKILL.md |
  109. | [Claude Code](https://code.claude.com/docs) | CC-\* | 170 | CLAUDE.md, .claude/rules/\*.md, settings.json, hooks, agents, skills, output styles, plugins, marketplace.json, .mcp.json |
  110. | [GitHub Copilot](https://docs.github.com/en/copilot) | COP-\*, CP-SK-\* | 35 | .github/copilot-instructions.md, .github/instructions/\*.instructions.md, .github/agents/, .github/prompts/, .github/hooks/\*.json, copilot-setup-steps.yml, plugin.json, .github/skills/ |
  111. | [Cursor](https://cursor.com) | CUR-\*, CR-SK-\* | 40 | .cursor/rules/\*.mdc, .cursorrules, .cursor/hooks.json, .cursor/agents/, .cursor/environment.json, .cursor/cli.json, permissions.json, .cursor-plugin/, .cursorignore, .cursor/skills/ |
  112. | [Codex CLI](https://developers.openai.com/codex) | CDX-\*, CX-SK-\* | 89 | AGENTS.md, .codex/config.toml, .codex/hooks.json, .codex/agents/\*.toml, .codex/rules/\*.rules, requirements.toml, .codex-plugin/plugin.json, .agents/skills/ |
  113. | [OpenCode](https://opencode.ai) | OC-\* | 68 | opencode.json(c), .opencode/agents/, .opencode/commands/, .opencode/tools/, .opencode/plugins/, .opencode/skills/ |
  114. | [Kiro](https://kiro.dev) | KIRO-\*, KR-SK-\*, KR-AG-\*, KR-HK-\*, KR-PW-\*, KR-MCP-\*, KR-SET-\*, KR-PM-\*, KR-WF-\*, KR-IGN-\* | 144 | .kiro/steering/\*\*/\*.md, .kiro/skills/\*\*/SKILL.md, .kiro/agents/\*\*/\*.{json,md}, .kiro/hooks/\*.kiro.hook, .kiro/hooks/\*.json, .kiro/settings/mcp.json, .kiro/settings/cli.json, .kiro/settings/permissions.yaml (or .json), .kiro/powers/\*/POWER.md and published POWER.md, power plugin.json and mcp.json, .kiro/workflows/\*.workflow.{json,yaml,yml}, .kiroignore |
  115. | [MCP](https://modelcontextprotocol.io) | MCP-\* | 30 | .mcp.json and the MCP server blocks of client configs |
  116. | [AGENTS.md](https://agents.md) | AGM-\*, XP-\* | 13 | AGENTS.md, AGENTS.local.md, AGENTS.override.md |
  117. | [Cline](https://docs.cline.bot) | CLN-\*, CL-SK-\* | 16 | .clinerules/, .cline/rules/, .cline/workflows/, .cline/hooks/, .clineignore, cline_mcp_settings.json, .cline/skills/ |
  118. | [Gemini CLI](https://github.com/google-gemini/gemini-cli) | GM-\* | 35 | GEMINI.md, .gemini/settings.json, gemini-extension.json, extension hooks and agents, .gemini/commands/\*.toml, policies, .gemini/agents/, .geminiignore |
  119. Continue, Aider, Amazon Q, Tabnine, Codeium, Devin/Windsurf and Amp are outside active support and monitoring. Shipped Amp and Windsurf/Devin validators remain available for legacy compatibility. Roo Code support was removed in 0.59.0.
  120. ## Architecture
  121. Rust workspace crates:
  122. - `agnix-rules` - rule metadata generated from `knowledge-base/rules.json`
  123. - `agnix-core` - shared validation engine library
  124. - `agnix-cli` - command-line interface binary
  125. - `agnix-lsp` - language server binary
  126. - `agnix-mcp` - MCP server binary
  127. - `agnix-wasm` - WebAssembly bindings for browser/runtime integrations
  128. ## Contributing
  129. Contributions welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for the development guide.
  130. ### Local development loop
  131. Run `bash scripts/preflight.sh` while editing. It checks formatting, rule
  132. bookkeeping, count tables, locale copies, instruction copies, and schema copies
  133. before any compilation. It requires Rust with rustfmt, Node.js, Python 3, and
  134. Bash. Missing tools fail the check instead of silently skipping it.
  135. Before pushing, run `bash scripts/preflight.sh --full`. This adds Clippy, workspace
  136. tests, the rule efficacy evaluation, the Kiro gate, packaging script tests,
  137. generated schema comparison, and source-built agent configuration validation.
  138. It reports each check's elapsed time and stops at the first failure. Schema
  139. comparison uses a temporary file and never overwrites local edits. Cargo builds,
  140. Rust tests, and Rayon default to two workers each; set `CARGO_BUILD_JOBS`,
  141. `RUST_TEST_THREADS`, or `RAYON_NUM_THREADS` to override these local defaults.
  142. The existing optional hook installer, `sh scripts/setup-hooks.sh`, installs a
  143. pre-push hook that calls the same full preflight. Git worktrees share the hooks
  144. directory, and the installer replaces the existing pre-push hook.
  145. Track the change in an issue, then open a PR with the tested commit, commands,
  146. results, and any limits of the evidence. Local preflight does not replace hosted
  147. Linux, Windows, macOS, CodeQL, dependency, or review gates. Review the diff and
  148. record a factual self-review comment, wait for successful `revuto-review` and
  149. CI, and address every review comment before merging through the PR. A changed
  150. head needs fresh checks and review. Report a specific blocker when a required
  151. gate cannot finish; keep branch protection intact.
  152. CI and Security cancel superseded runs of the same PR. Their main and scheduled
  153. runs use separate groups so newer runs cannot cancel them. The docs deployment
  154. workflow keeps its existing shared concurrency group. CodeQL uses Rust's buildless
  155. extraction, which runs build scripts and proc macros itself; release binaries are
  156. still built by the release workflow.
  157. [Report a bug](https://github.com/agent-sh/agnix/issues/new) | [Request a rule](https://github.com/agent-sh/agnix/issues/new) | [Good first issues](https://github.com/agent-sh/agnix/labels/good%20first%20issue)
  158. ## License
  159. MIT OR Apache-2.0
  160. ---
  161. <p align="center">
  162. <a href="https://github.com/agent-sh/agnix/stargazers">Star this repo</a> to help other developers find agnix.
  163. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.