"What is Hermes's defining architectural contribution?"	Self-evolving skills: the agent writes reusable procedures to persistent memory; available + auto-invoked in future sessions. Episodic memory that COMPOUNDS — each session makes the agent more capable. The deepest memory implementation in the roster.	harness-engineering::dd08::recall
"Why is Hermes's skill store a 'compounding' memory?"	Each session writes new skills; future sessions auto-invoke them. A skill learned in S1 is used in S2, S3, S4... The capability accumulates. No other harness has this.	harness-engineering::dd08::analysis
"Why is the self-evolving skill store a security risk?"	Model-initiated writes: the agent writes skills FREELY, no validation gate. A prompt-injected model can write a POISONED SKILL that activates on every future invocation — compounding damage. Worse than working-files poisoning (activates on USE, not just read).	harness-engineering::dd08::analysis
"Hermes scores 36/55 — highest on which module?"	Module 4 (Memory): 5/5. The self-evolving skill model is unmatched. All 5 memory tiers implemented. The memory reference.	harness-engineering::dd08::recall
"State the NemoClaw fix for Hermes's write surface."	Harness-managed writes (Module 4.3): model PROPOSES a skill; harness VALIDATES before persisting. The poisoned skill is rejected at the gate. Hermes's model-initiated writes become NemoClaw's harness-managed writes.	harness-engineering::dd08::application
"Hermes vs OpenClaw: which bet, and who won on OpenRouter?"	Hermes = depth play (self-evolving memory). OpenClaw = breadth play (40+ channels). Hermes overtook OpenClaw on OpenRouter May 10, 2026 (224B tokens/day). Depth won on that axis.	harness-engineering::dd08::recall