permission-manifest-guardInspects an OpenClaw skill directory before install or execution, translates declared and observed requirements into a human-readable permission manifest, an...
memory-refereeMemory hygiene and adjudication layer for OpenClaw agent workflows. Deduplicates entities, resolves naming conflicts, separates facts from goals from specula...
saturndayGoverned AI software execution — 48+ deterministic governance checks for Python with additional checks for TypeScript, DevOps, and project metadata. LLM-powe...