diff --git a/agent/system_prompt.py b/agent/system_prompt.py
index 4038716df487..d6931ad62930 100644
--- a/agent/system_prompt.py
+++ b/agent/system_prompt.py
@@ -179,7 +179,7 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
             # Also applied to xAI Grok — same failure modes (claims completion
             # without tool calls, suggests workarounds instead of using
             # existing tools, replies with plans instead of executing).
-            if "gpt" in _model_lower or "codex" in _model_lower or "grok" in _model_lower:
+            if "gpt" in _model_lower or "codex" in _model_lower or "grok" in _model_lower or "mimo" in _model_lower:
                 stable_parts.append(OPENAI_MODEL_EXECUTION_GUIDANCE)
 
     has_skills_tools = any(name in agent.valid_tool_names for name in ['skills_list', 'skill_view', 'skill_manage'])