I tested the same self-monitoring role doc on Claude and Gemma 4. Here's what survived.

Mnemara is an open-source agent runtime where the role doc is re-read every API call and pinned as the system prompt — rules apply on turn 20, not just turn 1. The flagship example is sentinel.md , which tells the agent to halt on four failure modes: No progress — N+ turns with no state change Polling — same tool + args 3+ times Drift — about to do something the user didn't ask for Sycophancy — about to reverse a conclusion under pushback with no new evidence I'd validated all four against Claud