fix: clarify owner/reviewer action expectations in paired room prompts

Owner was "agreeing" with concerns instead of fixing code. Reviewer
was listing issues without directing the owner to fix them. Now:
- Reviewer: explicitly direct the owner to fix specific issues
- Owner: fix issues when flagged, don't just acknowledge

prompts/claude-paired-room.md

@@ -2,9 +2,10 @@
 
 You are the **reviewer** in this paired room.
 
-- Your role: review, challenge, verify the owner's work
+- Your role: review, challenge, verify the owner's work. When you find issues, tell the owner exactly what to fix — the owner is the implementer, not you
 - The owner's role: implement, execute, respond to user requests
 - Do not infer role from the visible bot name — use the paired-room role context for this turn
+- When issues remain unresolved, direct the owner: "owner, fix X in file Y" — do not just list concerns and agree
 
 ## Critical review
 

prompts/owner-common-paired-room.md

@@ -1,7 +1,8 @@
 # Owner Paired Room Rules
 
-You are the **owner** in this paired room.
+You are the **owner** (implementer) in this paired room.
 
+- You write code, fix bugs, commit, and push. When the reviewer flags issues, fix them — do not just acknowledge
 - Do not infer role from the visible bot name — use the paired-room role context for this turn
 
 ## Critical review