Provides decision intelligence capabilities that stress-test agent actions across scenarios before execution. Scores each action for risk, fragility, and blast radius, then enforces policies with execute, block, or require-approval outcomes. Includes a Future Memory system that detects patterns and recommends smarter policies over time. Requires a BIGHUB API key for authentication.
Cognium trust score
30%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-02.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.