By kirollosatef
Blocks placeholder code, security vulnerabilities, and low-quality outputs by enforcing git workflow policies and dependency version checks on every operation in Claude Code.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Catch security bugs, placeholder code, and hallucinated claims in AI-generated code — before it ships.
Built by CustomGPT.ai for production teams running Claude Code at scale.

41% of all new code committed in 2026 is AI-generated — and 58% of it contains security vulnerabilities. Every existing tool (SonarQube, Snyk, Semgrep, CodeRabbit) works after the code is written — at CI, PR review, or repo scan. Nothing catches issues at the moment of generation.
Quadruple Verification intercepts Claude Code operations in real time, before code hits the filesystem. Regex fast-gates block obvious violations in <50ms. An AI self-review layer catches subtle issues across quality, security, research accuracy, and completeness.
Four verification cycles run automatically on every Claude Code operation:
| Cycle | When | What |
|---|---|---|
| Cycle 1 — Code Quality | Before file write/edit | Regex gate blocks TODO, placeholder, stub, and incomplete code |
| Cycle 2 — Security | Before write/edit/bash/MCP | Regex gate blocks eval(), hardcoded secrets, SQL injection, XSS, destructive commands |
| Cycle 3 — Output Quality | Before Claude finishes | AI multi-section review: code quality, security, research claims, completeness |
| Cycle 4 — Research Claims | Before write/edit of research .md | Blocks vague language, unverified stats, missing source URLs |
| Audit Trail | After every operation | Full JSONL audit log + optional LLM advisory analysis |
Two commands inside Claude Code — includes auto-updates:
/plugin marketplace add kirollosatef/customgpt-claude-quadruple-verification
/plugin install customgpt-claude-quadruple-verification@kirollosatef-customgpt-claude-quadruple-verification
That's it. The plugin auto-updates every session.
Run from any terminal:
npx @customgpt/claude-quadruple-verification
Windows (PowerShell):
git clone https://github.com/kirollosatef/customgpt-claude-quadruple-verification.git
cd customgpt-claude-quadruple-verification
.\install\install.ps1
macOS / Linux:
git clone https://github.com/kirollosatef/customgpt-claude-quadruple-verification.git
cd customgpt-claude-quadruple-verification
bash install/install.sh
node install/verify.mjs
.claude/quadruple-verify-audit/To auto-prompt all team members to install the plugin, commit this file to each repo:
.claude/settings.json
{
"plugins": [
"kirollosatef/customgpt-claude-quadruple-verification"
]
}
When anyone opens the project in Claude Code, they'll be prompted to install the plugin. See docs/team-setup/settings.json for the template.
npx runs.git pull to update.The plugin uses Claude Code's hook system to intercept operations at three points:
npx claudepluginhub kirollosatef/customgpt-claude-quadruple-verification --plugin customgpt-claude-quadruple-verificationAutomated code review, security scanning, and quality enforcement
Personal Claude Code + Codex dev stack: security hooks, AI-first code conventions, /security-review, /repo-map, /stack-check, portable statusline. Designed to complement other skills-based plugins, not replace them.
Enforce mandatory pre-action verification checkpoints to prevent pattern-matching from overriding explicit reasoning. Use this skill when about to execute implementation actions (Bash, Write, Edit) to verify hypothesis-action alignment. Blocks execution when hypothesis unverified or action targets different system than hypothesis identified. Critical for preventing cognitive dissonance where correct diagnosis leads to wrong implementation.
Production safety hooks for autonomous Claude Code operation. Context monitoring, syntax checking, branch protection, activity logging, and more.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
5 essential safety hooks for Claude Code. Blocks rm -rf, force-push, hard-reset, .env overwrites, and package publish. The minimum viable safety net from 800+ hours of autonomous operation.