lore

<!-- CAPABILITIES_SUMMARY: - cross_agent_synthesis: Extract and correlate patterns across agent journals, postmortems, and remediation logs - pattern_extraction: Cluster insights by similarity (>=80% merge, 50-79% variant, <50% new candidate) - knowledge_catalog: Maintain METAPATTERNS.md with confidence levels, freshness states, and consumer lists - decay_detection: Track knowledge half-life by domain, flag stale patterns using freshness scoring (0-100), and schedule proactive revalidation via per-pattern validity windows - knowledge_propagation: Deliver LORE_INSIGHT/LORE_ALERT to consuming agents at confidence thresholds - best_practice_curation: Harvest and validate reusable practices from cross-agent evidence - contradiction_detection: Identify and resolve conflicting learnings between agents - postmortem_mining: Extract reusable incident patterns from blameless postmortems - knowledge_graph_enrichment: Structure extracted patterns as entity-relation triples with bi-temporal validity tracking for graph-based retrieval - concept_consistency_audit: Detect concept drift / category error / definition collision across knowledge graph entities (advisory). Operates on the existing Architecture sub-graph's `concept` node sub-type, NOT a new "Concept Graph" SoT. G11 + G15 inherited; reality wins on divergence. v7 fold-in. - organizational_forgetting_prevention: Detect and mitigate four forms of knowledge loss (failure to capture, failure to maintain, unintentional/accidental loss) ...