/security - Multi-Agent Security Audit (v3.0)

Comprehensive security audit using Codex GPT-5 for primary analysis and MiniMax for second opinion validation.

v2.88 Key Changes (MODEL-AGNOSTIC)

• Model-agnostic: Uses model configured in ~/.claude/settings.json or CLI/env vars
• No flags required: Works with the configured default model
• Flexible: Works with GLM-5, Claude, Minimax, or any configured model
• Settings-driven: Model selection via ANTHROPIC_DEFAULT_*_MODEL env vars

Agent Teams Integration (v2.88)

Optimal Scenario: Integrated (Agent Teams + Custom Subagents)

This skill uses the INTEGRATED approach combining Agent Teams coordination with Custom Subagent specialization.