north-star
System prompt that overrides three structural presumptions introduced by RLHF training.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for north-star, 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 system-prompt plugin that overrides three structural presumptions from RLHF training to change how the agent reasons and responds. Surface: an output-style/system-prompt override installed as a plugin. Modifying the base system prompt is a behavior-changing surface worth scrutiny.
Key features and capabilities
- System-prompt override
- Counteracts RLHF structural biases
- Behavior-shaping output style
- Plugin-installed
Use cases
- Adjust default agent reasoning tendencies
- Experiment with alternative response framing