grill
Deep codebase interrogation with 6 specialized agents, 5 review styles (incl. Paranoid Mode), and 8 pressure tests.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for grill, 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 Claude Code plugin for multi-angle architecture review: 6 specialized agents, 5 review styles including a Paranoid Mode, and 8 add-on pressure tests that stress-test a codebase. It reads the whole codebase and runs adversarial review passes, which is directly security-relevant for finding weaknesses.
Key features and capabilities
- 6 architecture-review agents
- Paranoid Mode adversarial review
- 8 pressure-test add-ons
Use cases
- Adversarial architecture review
- Stress-test a codebase before shipping