Tracks agent behavior, decision-making processes, and failure points through structured observability. Provides session initiation and termination, step logging with actions and tool usage, decision point documentation with options and rationale, and error capture. Includes a CLI viewer for listing, viewing, and watching traces in real-time, plus trace analytics. Stores traces as local JSON files with no external dependencies.
Cognium trust score
63%
Tier
Scanned
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.