claude-crap

A Claude Code plugin that checks code quality around file edits and shell commands, using code metrics and security-analysis reports.

In plain words
What is it for?
Running checks before Write, Edit, and Bash actions, verifying changes afterward, applying a stop-time quality gate, measuring technical debt and syntax-tree metrics, and generating SARIF 2.1.0 reports.
Why use it?
It is intended to stop functional code from being written before a test safety net exists and to apply quality gates during development.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add ahernandez-developer/claude-crap
agentmods
npx agentmods add plugins/ahernandez-developer/claude-crap/plugin
Clone the repo
git clone --depth 1 https://github.com/ahernandez-developer/claude-crap

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-crap scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/.claude-plugin/plugin.json · 30 lines

What it actually says

{
  "$schema": "https://code.claude.com/schemas/plugin.json",
  "name": "claude-crap",
  "version": "0.4.8",
  "description": "Deterministic Quality Assurance plugin for Claude Code. Wraps every Write / Edit / Bash tool call with a PreToolUse gatekeeper, a PostToolUse verifier, and a Stop quality gate backed by CRAP index, Technical Debt Ratio, tree-sitter AST metrics, and SARIF 2.1.0 reports. Forbids the agent from writing functional code before a test safety net exists.",
  "author": {
    "name": "Alan Hernandez",
    "url": "https://github.com/ahernandez-developer"
  },
  "homepage": "https://github.com/ahernandez-developer/claude-crap",
  "repository": "https://github.com/ahernandez-developer/claude-crap",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "claude-code-plugin",
    "quality-assurance",
    "sast",
    "sarif",
    "crap-index",
    "technical-debt",
    "quality-gate",
    "shift-left",
    "deterministic",
    "mutation-testing",
    "mcp-server",
    "mcp",
    "tree-sitter"
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 30 lines scan A b4890b589292

Subscribe to this mod's changes

claude-crap is a plugin published in the GitHub repository ahernandez-developer/claude-crap (7 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.