Updated 1d ago
by agent-sh
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.
470 GitHub stars (470)
+30 in 30 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | −1 |
| Sep 29 | +1 |
| Sep 30 | +2 |
| Oct 1 | +1 |
| Oct 2 | +8 |
| Oct 3 | +2 |
| Oct 4 | 0 |
| Oct 5 | +2 |
| Oct 6 | −1 |
| Oct 7 | +4 |
| Oct 8 | +1 |
| Oct 9 | +1 |
| Oct 10 | 0 |
| Oct 11 | −1 |
| Oct 12 | +1 |
| Oct 13 | +2 |
| Oct 14 | +1 |
| Oct 15 | +1 |
| Oct 16 | +3 |
| Oct 17 | 0 |
| Oct 18 | +1 |
| Oct 19 | +1 |
| Oct 20 | 0 |
| Oct 21 | +1 |
| Oct 22 | 0 |
| Oct 23 | +1 |
| Oct 24 | 0 |
| Oct 25 | 0 |
| Oct 26 | +1 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | +4 |
| Oct 30 | 0 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | +2 |
| Nov 3 | +3 |
| Nov 4 | 0 |
| Nov 5 | +3 |
- 28 skills (28 skills found in its SKILL.md files)
- 37 forks (37 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add agent-sh/agnix
Asks which skills and agents to install. Just one: npx skills add agent-sh/agnix --skill agnix — add -g for every project.
Claude Code
git clone https://github.com/agent-sh/agnixcp -r "agnix/skills/agnix" ~/.claude/skills/
Copies the agnix skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add agent-sh/agnix
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 28 of 88 files.
-
agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 702 rules.
skills/agnix/ on GitHub (opens in a new tab)SKILL.md -
deep-reference
Use when validating deep references
tests/fixtures/ on GitHub (opens in a new tab)skills/ deep-reference/ SKILL.md -
long-body
Use when testing the AS-021 token estimate on a long skill body.
tests/fixtures/ on GitHub (opens in a new tab)skills/ long-body/ SKILL.md -
missing-frontmatter
No description in the SKILL.md.
tests/fixtures/ on GitHub (opens in a new tab)skills/ missing-frontmatter/ SKILL.md -
portable-rules
Release helper for tagging builds.
tests/fixtures/ on GitHub (opens in a new tab)skills/ portable-rules/ SKILL.md -
windows-path
Use when validating windows paths
tests/fixtures/ on GitHub (opens in a new tab)skills/ windows-path/ SKILL.md -
agent-without-context-skill
Use when testing agent without context validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ agent-without-context/ SKILL.md -
hint-skill
Use when testing argument hints
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ argument-hint-no-args/ SKILL.md -
argument-placeholder-in-code
Use when listing the processes that use the most memory
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ argument-placeholder-in-code/ SKILL.md -
deploy-prod
Deploys to production
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ deploy-prod/ SKILL.md -
reference-skill
Use when looking up documentation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ fork-no-instructions/ SKILL.md -
indexed-arguments-no-hint
Use when validating indexed arguments
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ indexed-arguments-no-hint/ SKILL.md -
invalid-agent-skill
Use when testing invalid agent validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ invalid-agent/ SKILL.md -
invalid-context-skill
Use when testing invalid context validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ invalid-context/ SKILL.md -
hooks-skill
Use when testing hooks validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ invalid-hooks/ SKILL.md -
invalid-model-skill
Use when testing invalid model validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ invalid-model/ SKILL.md -
invalid_name
Use when user wants to review code
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ invalid-name/ SKILL.md -
directory-helper
Use when validating name-directory matching
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ name-directory-mismatch/ SKILL.md -
bad-bool-skill
Use when testing boolean type validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ string-boolean-disable/ SKILL.md -
bad-invocable-skill
Use when testing boolean type validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ string-boolean-invocable/ SKILL.md -
too-many-injections-skill
Use when testing injection limit validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ too-many-injections/ SKILL.md -
unknown-frontmatter-field
Use when validating frontmatter keys
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ unknown-frontmatter-field/ SKILL.md -
unknown-tool-skill
Use when testing unknown tool validation
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ unknown-tool/ SKILL.md -
helper
Use when validating vague skill names
tests/fixtures/ on GitHub (opens in a new tab)invalid/ skills/ vague-name/ SKILL.md -
code-review
Use when user asks to review code for quality and security issues.
tests/fixtures/ on GitHub (opens in a new tab)valid/ skills/ code-review/ SKILL.md -
fork-with-instructions
Use when analyzing code quality
tests/fixtures/ on GitHub (opens in a new tab)valid/ skills/ fork-with-instructions/ SKILL.md -
inline-authorized-skill
Use when explicitly authorizing internal automation
tests/fixtures/ on GitHub (opens in a new tab)valid/ skills/ inline-authorized-skill/ SKILL.md -
social-source-evidence
Use when reviewing X/Twitter exports as source evidence for social content decisions.
tests/fixtures/ on GitHub (opens in a new tab)valid/ skills/ social-source-evidence/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.