Export

# Red vs Blue Security Simulation

A multi-agent system where a Red Team agent finds vulnerabilities in a system, a Blue Team agent patches them, and a Security Auditor scores the system and decides whether to run another attack round or stop.

## Orchestration instructions (chief)

Split the task into ordered steps and start the chain.

## Roles
- **red-team** (Sub-agent): Finds new vulnerabilities in the system — technical flaws, logic flaws, or social engineering angles. Use proactively at the start of each round.
- **blue-team** (Sub-agent): Proposes patches and mitigations for currently open vulnerabilities. Use proactively after Red Team finds new vulnerabilities each round.
- **security-auditor** (Sub-agent): Reviews vulnerabilities and patches, calculates a security score, and decides whether the attack/defense loop continues or stops.

## Workflow
- **Chief:** Chief — splits tasks and delegates.
- **Sequential: Sequential** (run in order, passing output (handoff)) → red-team → blue-team → security-auditor
  - Execution: run the child agents one by one in the order above; pass each step's output as input to the next.

## Coordination / communication
- Chief → Sequential: output handed to the next