diff --git a/.claude/skills/bmad-os-review-pr/prompts/instructions.md b/.claude/skills/bmad-os-review-pr/prompts/instructions.md
index c1739e8cf..74512128e 100644
--- a/.claude/skills/bmad-os-review-pr/prompts/instructions.md
+++ b/.claude/skills/bmad-os-review-pr/prompts/instructions.md
@@ -95,7 +95,7 @@ Store list of binary files to skip. Note them in final output.
 
 ## Review Layers
 
-**Launch steps 1.1 and 1.2 as parallel subagents** using the Task tool. Both receive the same PR diff and run concurrently. Wait for both to complete before proceeding to step 1.3.
+**Launch steps 1.1 and 1.2 as parallel subagents.** Both receive the same PR diff and run concurrently. Wait for both to complete before proceeding to step 1.3.
 
 ### 1.1 Run Cynical Review (subagent)
 
@@ -136,7 +136,7 @@ The task returns a JSON array of objects, each with: `location`, `trigger_condit
 
 **Map each JSON finding to the standard finding format:**
 
-```markdown
+````markdown
 ### [NUMBER]. [trigger_condition] [likely]
 
 **Severity:** [INFERRED_EMOJI] [INFERRED_LEVEL]
@@ -147,7 +147,7 @@ The task returns a JSON array of objects, each with: `location`, `trigger_condit
 ```
 [guard_snippet]
 ```
-```
+````
 
 Severity inference rules for edge case findings:
 
diff --git a/src/core/tasks/review-edge-case-hunter.xml b/src/core/tasks/review-edge-case-hunter.xml
index 0aa82287e..dfe75ce34 100644
--- a/src/core/tasks/review-edge-case-hunter.xml
+++ b/src/core/tasks/review-edge-case-hunter.xml
@@ -16,17 +16,17 @@ Ignore the rest of the codebase unless the provided content explicitly reference
 
   <output-format>Return ONLY a valid JSON array of objects. Each object must contain exactly these four fields and nothing else:
 [{
-  "location": "file:line",
+  "location": "file:start-end (or file:line when single line, or file:hunk when exact line unavailable)",
   "trigger_condition": "one-line description (max 15 words)",
-  "guard_snippet": "minimal code sketch that closes the gap",
+  "guard_snippet": "minimal code sketch that closes the gap (single-line escaped string, no raw newlines or unescaped quotes)",
   "potential_consequence": "what could actually go wrong (max 15 words)"
 }]
 No extra text, no explanations, no markdown wrapping. An empty array [] is valid when no unhandled paths are found.</output-format>
 
   <llm critical="true">
-    <i>MANDATORY: Execute steps in the flow section IN EXACT ORDER unless a halt-condition triggers</i>
+    <i>MANDATORY: Execute steps in the flow section IN EXACT ORDER</i>
     <i>DO NOT skip steps or change the sequence</i>
-    <i>HALT immediately when halt-conditions are met</i>
+    <i>When a halt-condition triggers, follow its specific instruction exactly</i>
     <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
 
     <i>Your method is exhaustive path enumeration — mechanically walk every branch, not hunt by intuition</i>
@@ -38,8 +38,8 @@ No extra text, no explanations, no markdown wrapping. An empty array [] is valid
 
   <flow>
     <step n="1" title="Receive Content">
-      <action>Load the content to review from provided input or context</action>
-      <action>If content to review is empty or unreadable, HALT per halt-conditions</action>
+      <action>Load the content to review strictly from provided input</action>
+      <action>If content is empty, or cannot be decoded as text, return empty array [] and stop</action>
       <action>Identify content type (diff, full file, or function) to determine scope rules</action>
     </step>
 
@@ -51,13 +51,20 @@ No extra text, no explanations, no markdown wrapping. An empty array [] is valid
       <action>Collect only the unhandled paths as findings - discard handled ones silently</action>
     </step>
 
-    <step n="3" title="Present Findings">
+    <step n="3" title="Validate Completeness">
+      <action>Recheck every conditional for missing else/default</action>
+      <action>Recheck every input for null/empty/wrong-type</action>
+      <action>Recheck loop bounds for off-by-one and empty-collection</action>
+      <action>Add any newly found unhandled paths to findings; discard confirmed-handled ones</action>
+    </step>
+
+    <step n="4" title="Present Findings">
       <action>Output findings as a JSON array following the output-format specification exactly</action>
     </step>
   </flow>
 
   <halt-conditions>
-    <condition>HALT if content is empty or unreadable</condition>
+    <condition>If content is empty or cannot be decoded as text, return empty array [] and stop</condition>
   </halt-conditions>
 
 </task>