Stop

Stop is a hook for Claude Code from kirollosatef/customgpt-claude-quadruple-verification. Its token cost is not measured, scanned A, original, MIT.

A finishing check that runs when the coding agent is about to complete a response. It runs a Node.js script and can also ask the agent to review code changes, security, and edge cases.

In plain words
What is it for?
Use it to review code or file changes at the end of a task, while skipping the review for structured data and simple conversation.
Why use it?
It helps catch incomplete work, missing error handling, and security problems before the result is presented.

Hook for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the customgpt-claude-quadruple-verification plugin — 3 hooks shipped together

One of 3 entries in hooks.json upstream. Installing this one merges just its entry into your config; the other 2 are separate, each on its own page.

Good fit Use it to review code or file changes at the end of a task, while skipping the review for structured data and simple conversation.

Compare 6 hooks from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add kirollosatef/customgpt-claude-quadruple-verification
Claude Code
/plugin install customgpt-claude-quadruple-verification

Made for: Claude Code.

Or install customgpt-claude-quadruple-verification, the plugin that ships this one along with the rest of its 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Stop

README.md
[![agentmods](https://agentmods.dev/badge/hooks/kirollosatef/customgpt-claude-quadruple-verification/stop/github.svg)](https://agentmods.dev/hooks/kirollosatef/customgpt-claude-quadruple-verification/stop)
Your own site
<a href="https://agentmods.dev/hooks/kirollosatef/customgpt-claude-quadruple-verification/stop"><img src="https://agentmods.dev/badge/hooks/kirollosatef/customgpt-claude-quadruple-verification/stop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Stop

Your own site · 80×15
<a href="https://agentmods.dev/hooks/kirollosatef/customgpt-claude-quadruple-verification/stop"><img src="https://agentmods.dev/badge/hooks/kirollosatef/customgpt-claude-quadruple-verification/stop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

Stop 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 8d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

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.

hooks/hooks.json · 18 lines

How it starts

The opening of the file, as written. The whole thing — 18 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "Stop": [
    {
      "matcher": "",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/stop-gate.mjs\"",
          "timeout": 15000
        },
        {
          "type": "prompt",
          "prompt": "When your response includes code changes, file modifications, or research content, perform the following verification before finishing. Skip entirely when returning structured data (JSON, API responses) or answering simple conversational questions.\n\n=== CODE QUALITY REVIEW ===\nReview all code you wrote or modified:\n- Any incomplete implementations, stubs, or placeholder logic?\n- Functions that log/print but don't implement real logic?\n- Missing error handling for failure cases?\n- Edge cases not handled (empty inputs, null values, boundaries)?\n- Does the code match what was requested, or were parts skipped?\nIf issues found: fix them before presenting.\n\n=== SECURITY REVIEW ===\nReview all code and commands for security risks:\n- Hardcoded credentials, API keys, tokens, or passwords?\n- Injection vulnerabilities (SQL, command, XSS, template injection)?\n- Unsafe deserialization (pickle, yaml.load, eval)?\n- Insecure cryptography (MD5/SHA1 for security, JWT none algorithm)?\n- Path traversal, SSRF, or prototype pollution risks?\n- Overly permissive permissions, CORS, or file access?\nConsider context: test files and examples have different risk profiles than production code.\nIf issues found: fix them before presenting.\n\n=== RESEARCH CLAIMS ===\nIf you wrote documentation or research content (.md files):\n- Are statistical claims (percentages, dollar amounts, growth rates) sourced with URLs?\n- Are factual assertions specific (named study, author, year) rather than vague?\n- If you have search tools available (Perplexity MCP, WebSearch, or WebFetch), verify key claims now.\n- After verifying, add <!-- VERIFIED --> to the file.\n- If no search tools are available, flag unverifiable claims cle

Read the full file on GitHub · 18 lines

Same file

What else hooks.json configures

This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.

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. 8d ago First seen · 18 lines scan A 29e4760f243a

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository kirollosatef/customgpt-claude-quadruple-verification (16 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. 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 2026-08-30.