Provides explicit, governed long-term memory for Claude Code with per-repository isolation. Each git repository maps to its own memory thread, ensuring scoped storage and retrieval. Supports storing general notes, coding preferences, and architectural decisions with full provenance tracking. Memories persist across sessions and are searchable via the Sovant dashboard.
Cognium trust score
97%
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 2026-09-19.
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.