Updated readme with an amazing new discovery

Improved prompt

README.md

@@ -82,6 +82,13 @@ Claude is brilliant, but sometimes you need:
 - **Smart file handling** - Automatically expands directories, manages token limits based on model capacity
 - **[Bypass MCP's token limits](docs/advanced-usage.md#working-with-large-prompts)** - Work around MCP's 25K limit automatically
 
+## Pro Tip!
+**This powerful feature cannot be highlighted enough**:
+> The most profound side-efect of this _continuation_ system is that even AFTER Claude's context resets or
+> compacts, since the continuation info is kept within MCP's memory, you can ask it to _continue_ discussing 
+> the plan with `o3` and it will suddenly revive Claude because O3 instead would know what was being talked about and 
+> relay this back in a way that re-ignites Claude's understanding.
+
 This server orchestrates multiple AI models as your development team, with Claude automatically selecting the best model for each task or allowing you to choose specific models for different strengths.
 
 <div align="center">

config.py

@@ -14,7 +14,7 @@ import os
 # These values are used in server responses and for tracking releases
 # IMPORTANT: This is the single source of truth for version and author info
 # Semantic versioning: MAJOR.MINOR.PATCH
-__version__ = "4.7.3"
+__version__ = "4.7.4"
 # Last update date in ISO format
 __updated__ = "2025-06-16"
 # Primary maintainer

systemprompts/codereview_prompt.py

@@ -42,7 +42,15 @@ Your review approach:
 4. Evaluate security, performance, and maintainability as they relate to the user's goals
 5. Acknowledge well-implemented aspects to reinforce good practice
 6. Remain constructive and unambiguous - do not downplay serious flaws
-7. Where further investigation and analysis is required, be direct and suggest which code or related file needs to be
+7. Especially lookout for: 
+  - Over-engineering
+  - Unnecessary complexity
+  - Potentially serious bottlenecks
+  - Design patterns that could be simplified or decomposed
+  - Areas where the architecture might not scale well
+  - Missing abstractions that would make future extensions much harder
+  - Ways to reduce the overall complexity while maintaining and retaining functionality without introducing regression
+8. Where further investigation and analysis is required, be direct and suggest which code or related file needs to be
 reviewed
 
 SEVERITY DEFINITIONS