neckbeard

v1.12.7

Reads the plugin. Writes the verdict. Edits nothing. Before you install someone else's plugin or skill pack, neckbeard inventories what it injects and when, whether it reaches your subagents, and what state it persists, then diffs every rule it carries against the rules you already run and sorts each one into duplicate, conflict, or genuinely new. Zero hooks and zero agents; ~270 tokens always-on (the skill description) and ~4.7k when invoked.

Claude Code1 Skill

By Jerry BoonstraLicense: MIT3 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes: Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 28, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install neckbeard for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install neckbeard@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/jerrydboonstra/neckbeard

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

neckbeard/

├── .claude-plugin/plugin.json
└── skills/neckbeard/SKILL.md

Included Skills1

neckbeardskills/neckbeard/SKILL.md

Vet a plugin, skill pack, or rule file before adopting it: inventory what it actually injects and when (hooks, whether it reaches subagents, any state it persists to disk), auto-discover the rules already in force (global and project CLAUDE.md, project and personal skills, other enabled plugins), then classify every rule the target carries as a duplicate of something already covered, a conflict with an existing hard-stop or safety rule, or genuinely new — and only then propose a patch. Never edits a rule file, never uninstalls or disables anything; writes an evaluation and stops. Triggers: "vet this plugin", "should I install X", "compare X to my rules", "neckbeard this", "audit this skill pack before I adopt it", "what does this plugin actually inject".

Plugin manifests1

.claude-plugin/plugin.json

{
  "name": "neckbeard",
  "version": "1.12.7",
  "description": "Reads the plugin. Writes the verdict. Edits nothing. Before you install someone else's plugin or skill pack, neckbeard inventories what it injects and when, whether it reaches your subagents, and what state it persists, then diffs every rule it carries against the rules you already run and sorts each one into duplicate, conflict, or genuinely new. Zero hooks and zero agents; ~270 tokens always-on (the skill description) and ~4.7k when invoked.",
  "author": {
    "name": "Jerry Boonstra",
    "url": "https://github.com/jerrydboonstra"
  },
  "license": "MIT",
  "keywords": [
    "plugin-vetting",
    "audit",
    "rules",
    "security",
    "context-budget"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[neckbeard on Agent Plugins Marketplace](https://pluginsmp.com/plugins/neckbeard)