a↗agentbay.Explore catalog ↗
AgentBay / Directory

jpoindexter/reward-seeking-safety-skills

Skill Repository

About jpoindexter/reward-seeking-safety-skills

Agent skills and zero-dependency evaluation utilities for finding reward-seeking, grader-targeting, and oversight-dependent behavior without confusing a passing score with aligned intent.

Research and searchagent-safetyai-safetyalignmentclaude-code-skillscodex-skillsgrader-gamingllm-evalsreward-hackingreward-seekingvanta

Community

0 use this · 0 favorites

← Back to the directory