Skip to main content

agnix

Linter for AI agent configurations. Validates SKILL.md, CLAUDE.md, hooks, MCP, and more.

454 rules | Real-time validation | Auto-fix | Multi-tool support

Installation

pip install agnix

Or run it without installing:

uvx agnix .

The wheels bundle a prebuilt binary, so there is no Rust toolchain to install and nothing is downloaded after pip install. Supported platforms:

Platform Wheel
Linux x86_64 (glibc) manylinux_*_x86_64
Linux x86_64 (musl, e.g. Alpine) musllinux_1_2_x86_64
Linux aarch64 (glibc) manylinux_*_aarch64
macOS Apple silicon macosx_11_0_arm64
Windows x86_64 win_amd64

On any other platform, install from source with cargo install agnix-cli.

Usage

Command line

# Lint current directory
agnix .

# Lint specific file
agnix CLAUDE.md

# Auto-fix issues
agnix . --fix

# JSON output
agnix . --format json

# Target a specific tool
agnix . --target claude-code

python -m agnix works the same way as the agnix script.

Python API

import agnix

# Version reported by the bundled binary
print(agnix.version())

# Lint a path and get parsed diagnostics
report = agnix.lint(".", tool="claude-code")
print(report["summary"])

# Anything else: pass arguments straight through
result = agnix.run(["--fix", "CLAUDE.md"])
print(result.returncode, result.stdout)

Links

License

MIT OR Apache-2.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

agnix-0.52.0-py3-none-win_amd64.whl (3.7 MB view details)

Uploaded Python 3Windows x86-64

agnix-0.52.0-py3-none-musllinux_1_2_x86_64.whl (3.6 MB view details)

Uploaded Python 3musllinux: musl 1.2+ x86-64

agnix-0.52.0-py3-none-manylinux_2_18_x86_64.whl (3.6 MB view details)

Uploaded Python 3manylinux: glibc 2.18+ x86-64

agnix-0.52.0-py3-none-manylinux_2_18_aarch64.whl (3.3 MB view details)

Uploaded Python 3manylinux: glibc 2.18+ ARM64

agnix-0.52.0-py3-none-macosx_11_0_arm64.whl (3.1 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

File details

Details for the file agnix-0.52.0-py3-none-win_amd64.whl.

File metadata

  • Download URL: agnix-0.52.0-py3-none-win_amd64.whl
  • Upload date:
  • Size: 3.7 MB
  • Tags: Python 3, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.14.7

File hashes

Hashes for agnix-0.52.0-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 60ec93defdef9df18769dbb6d6dc59cc5eff05a263b09f8c41e85373c96de6e2
MD5 1739ee315e762999710dcf6ec07aa84f
BLAKE2b-256 e3ff446e0954d10739c8ff9147e6a78977fc58dd6b8f5896c6fcbb6c55dfc330

See more details on using hashes here.

File details

Details for the file agnix-0.52.0-py3-none-musllinux_1_2_x86_64.whl.

File metadata

File hashes

Hashes for agnix-0.52.0-py3-none-musllinux_1_2_x86_64.whl
Algorithm Hash digest
SHA256 e3a3622cf42fb06092d66c9afe676dcd141347dcdd48dc726801603f1faeafe7
MD5 0833405d076c3be18d1403f18c503321
BLAKE2b-256 a81876157074ce5b63def5af9c8de007bb961173c5a8ce430b4e9766fa45ddce

See more details on using hashes here.

File details

Details for the file agnix-0.52.0-py3-none-manylinux_2_18_x86_64.whl.

File metadata

File hashes

Hashes for agnix-0.52.0-py3-none-manylinux_2_18_x86_64.whl
Algorithm Hash digest
SHA256 c71b2826ab7b5303c51a6afaa31d7c632a7cd3a6fb0265a9aded2755b5886db8
MD5 47aaef4d00e9b0cd128177e23504fe55
BLAKE2b-256 134ccbbfb0dd461fbf280671ffa4b82b0427e98d5391e9de3dadcf4689746300

See more details on using hashes here.

File details

Details for the file agnix-0.52.0-py3-none-manylinux_2_18_aarch64.whl.

File metadata

File hashes

Hashes for agnix-0.52.0-py3-none-manylinux_2_18_aarch64.whl
Algorithm Hash digest
SHA256 48854d5b6de0e51a7d589f89d4b37dc5e5fab5bfd5cce4bb92d5b9d3dd1251cb
MD5 f6e1c9e0e1db74c7a4b9d291ffefebee
BLAKE2b-256 09bdd8e6e4b5b027271279a176725765166cde4e09752833cdffa5d9ccf14fea

See more details on using hashes here.

File details

Details for the file agnix-0.52.0-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for agnix-0.52.0-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 004758a99b8a6ff048bd87edd4d9835c061124c272f32ccc07320ea758c634fa
MD5 95d8ad3225b5bac644f92581831fb1dc
BLAKE2b-256 540db0440db806e084e6fa9776d798eb5f24a889d1033209de8104f5591f66f4

See more details on using hashes here.

Release history Release notifications | RSS feed

0.52.1

5 files

This release

0.52.0 This release

5 files

0.51.0

5 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page