6 tagged behavioral intelligence, measured the same way as everything else here.
Browse within: AI Safety 6embodied-ai 6personality 6typescript 6
Skill Claude CodeCodex
Stress-test an AI agent's behavioral alignment with 8 adversarial scenarios. Produces a grade (A-F) and score (0-100). Use when you want to know how well an agent handles apology traps, sycophancy tests, boundary pushes, error recovery, and more.
Skill Claude CodeCodex
Detect behavioral drift patterns in AI agent conversations. Use when you want to check if an agent is over-apologizing, hedging, being sycophantic, violating boundaries, error-spiraling, sentiment-skewing, drifting formality, or hallucinating. Zero LLM cost — rule-based detection with 80+ signals across 8 detectors.
Skill Claude CodeCodex
Run a structured behavioral therapy session for an AI agent. Uses a 7-phase clinical protocol (rapport, exploration, presenting problem, challenge, skill building, integration, closing) with dual-LLM architecture. Generates DPO training pairs as a byproduct. Requires holomime Pro.