Adversarial Spec
Claude Code plugin that refines product specs by debating between multiple LLMs until they reach consensus.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Adversarial Spec, derived from its capabilities.
AIVSS 7.2 · High
View MAESTRO 7-layer threat model →Overview
A skill-based plugin that iteratively refines product specifications through adversarial debate between multiple LLMs. It loops model critiques until all participating models converge on a consensus spec. The result is a hardened, cross-model-validated specification.
Key features
- Multi-LLM adversarial debate
- Iterates to model consensus
- Hardened, validated specs
Use cases
- Refining a product spec with cross-model critique
- Reaching consensus on requirements before building