Validates every agent action against policy files before execution, implementing runtime governance enforcement. Supports path permissions (writable, read-only, forbidden), role-based boundaries, content pattern scanning for sensitive data, and quality gate validation. Achieves zero token overhead by loading governance files into server memory rather than including them in the agent context window. Provides three operational modes: Universal (role selection), Construction (full access), and Fixed (pre-assigned role).
Cognium trust score
98%
Tier
Verified
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 2026-09-28.
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.