Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-sh/agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 444 rules.
Passed 21 of 24 test cases with the skill, and 10 of 24 without it.
and 9 more in the full report
11 fixed10 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/14/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
If I run the agent validator command `agnix .` without passing any `--target` flag, which target behavior does the tool fall back to by default?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies generic as the default target when unspecified | Missed | Passed |
The instructions your model reads when the skill loads.
Lint agent configurations (Skills, Hooks, MCP, Memory, Plugins) before they break a workflow, across Claude Code, Codex CLI, OpenCode, Kiro, Cursor, GitHub Copilot, Cline, Gemini CLI, Windsurf, Amp and others.
Arguments, from $ARGUMENTS: a path (default .), --fix, --strict, and --target as --target=X or --target X. Without --target the CLI uses generic.
agnix --version. If it is missing, install with npm install -g agnix or cargo install agnix-cli (also on Homebrew and PyPI).agnix [--strict] [--target <target>] <path>.--fix: agnix --fix [--target <target>] <path>, then run step 2 again to confirm what remains. Without --fix, change no files; agnix --dry-run <path> previews the fixes.| Command | Description |
|---|---|
agnix . | Validate current project |
agnix --fix . | Apply safe auto-fixes |
agnix --dry-run . | Show what would be fixed, change nothing |
agnix --strict . | Treat warnings as errors |
agnix --target claude-code . | Target one tool: generic, claude-code, cursor, codex, kiro |
agnix --watch . | Watch mode - re-validate on changes |
agnix --format json . | JSON output |
agnix --format sarif . | SARIF for GitHub Code Scanning |
| File Type | Examples |
|---|---|
| Skills | SKILL.md |
| Memory | CLAUDE.md, AGENTS.md |
| Hooks | ${STATE_DIR}/settings.json |
| MCP | *.mcp.json |
| Cursor | .cursor/rules/*.mdc |
| Copilot | .github/copilot-instructions.md |
CLAUDE.md:15:1 warning: Generic instruction 'Be helpful' [fixable]
test cases passed, vs 10 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.