Verify factual claims against live web sources before asserting them. Use when about to state a fact you are not certain of (a date, number, name, statistic), or before publishing AI-generated text that makes factual claims. Returns a verdict (supported/refuted/unverified), a confidence score, and citations.
Use when working with agent, multi-agent, pipeline, orchestration, tool use, memory, context. Multi-agent systems: pipelines, orchestration, verification, semantic integrity.
Use for reading/writing structured memory blocks, hash-chain audit, session logs. Replaces flat STATE.MD with typed JSON blocks and provenance chain. Load when starting/ending sessions, recording decisions, or verifying facts.
Use when creating a new artifact or checking if something already exists. Artifact registry of all created scripts, benchmarks, prototypes, data, templates. Cross-reference with dso.md for verified patterns.