Provides a shared in-memory cache where Claude Code subagents check before reading and record after reading, turning redundant file reads into cheap cache lookups. Includes staleness detection via file modification time and a session map for planning. Designed as a Claude Code plugin with automatic protocol injection.
Cognium trust score
100%
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.