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.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
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 and capabilities
- 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