New Guide — Security skill for Claude Code
Create a new security guide using the full multi-agent workflow.
How to install New Guide
Installs to ~/.claude/commands/twodragon0-claudesec-new-guide.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Twodragon0/claudesec/HEAD/.claude/commands/new-guide.md -o ~/.claude/commands/twodragon0-claudesec-new-guide.md Restart Claude Code, or start a new session, for it to be picked up.
What New Guide does
description: Create a new security guide using the full multi-agent workflow
Create a new security guide end-to-end using coordinated agents:
**Topic**: $ARGUMENTS
Workflow (5-stage pipeline)
Stage 1: Research (sec-researcher)
- Research the topic using authoritative sources (OWASP, NIST, CIS)
- Identify key threats, mitigations, and best practices
- Produce a research brief with source citations
Stage 2: Implementation (sec-implementer)
- Create any scanner rules, hooks,
Alternatives in Security
- Defense In Depth — Implement multi-layered testing and security best practices 98.1k ★
- Pal — Multi-model AI integration — chat, debugging, code review, planning, security audit 11.3k ★
- T3mp3st — autonomous red teaming platform; multi-agent offensive-security meta-harness 5.7k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Multi Tenant Fullstack Crud Skill
A full-stack CRUD Agent Skill for building production-ready multi-tenant web apps with role-based access, audi
Skill Code Review
Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
Pocketpaw
Your AI agent in 30 seconds. Not 30 hours. Self-hosted, open-source personal AI with desktop installer, multi-
Raptor Loop Hunt
RAPTOR autonomous looping multi-altitude security vulnerability hunt — Claude Code skill
Postgres
Execute safe read-only SQL queries against PostgreSQL databases with multi-connection support and defense-in-d
Vuln Scan
Multi-agent security vulnerability sweep — fans out region-scoped hunters, verifies findings, and reports
Related Agents
Critic Security
Review code for OWASP-style security issues (injection, authn/authz, secrets, supply chain, LLM-specific) in p
Auto Claude
by AndyMik90 - Autonomous multi-agent coding framework for Claude Code (Claude Agent SDK) that integrates the
Dashclaw Gate Runner
Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa