Foundry Security Spec

This implements Cisco's Foundry specification for building multi-agent security evaluation systems. It's not a tool you install but a blueprint defining 8 core agent roles (Orchestrator, Planner, Navigator, Detector, Explorer, Validator, Investigator, Publisher) that coordinate to find and validate security issues. The workflow walks you through adopting the constitution's 11 principles via spec-kit, then clarifying integration choices for your environment (which LLM provider, what datastore, deployment target) before generating your customized specification. Good if you're building automated security testing that needs structured coordination between AI agents rather than one monolithic prompt. The detection-to-prevention flywheel is clever: explorers find novel issues that become codified rules for future runs.

Install to Claude Code

npx -y skills add aradotso/security-skills --skill foundry-security-spec --agent claude-code