miracle-security

Community

Multi-agent security reviews for code & enterprise

Authorvasilievyakov
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Code review and security assessments can be inconsistent when done by a single pass or a single reviewer. Miracle Security provides five parallel audit agents for code review and four evaluators for enterprise assessment, delivering more reliable, converged findings and a clear maturity view.

Core Features & Use Cases

  • Mode 1: Code Review — five agents scan for OWASP Top 10, secrets leaks, authentication issues, dependency risks, and logic flaws.
  • Mode 2: Enterprise Assessment — four evaluators assess data handling, access control, compliance readiness, and operational resilience, producing a risk maturity scorecard.
  • Threat model calibration — threat profile adjusts severity for deployment context to reduce false positives.
  • Architecture — follows the /directors pattern for coordinating agents and directors.
  • Use Case — pre-release security audits, enterprise sales readiness, and regression checks.

Quick Start

Trigger /security review or /security assess to start the appropriate multi-agent security workflow.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: miracle-security
Download link: https://github.com/vasilievyakov/miracle-infrastructure/archive/main.zip#miracle-security

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.