Close three review blind spots found by defect tracing

Live eval deliverables shipped five polish defects; tracing each through
the transcripts showed three mechanisms, each now addressed:
- reviewers answered pointed checklist items with unsupported yes
  (evidence rule: every What-to-Check answer needs file:line evidence)
- no reviewer ever saw the design's global constraints (controllers now
  paste binding constraints into task requirements)
- test output noise was invisible everywhere (pristine-output checks in
  implementer self-review and quality review)

skills/subagent-driven-development/code-quality-reviewer-prompt.md

@@ -61,6 +61,9 @@ Subagent (general-purpose):
     running it. If you cannot run commands in this environment, name the
     test you would run.
 
+    Warnings or other noise in the implementer's reported test output are
+    findings — test output should be pristine.
+
     ## What to Check
 
     **Code quality:**
@@ -81,6 +84,9 @@ Subagent (general-purpose):
       significantly grow existing files? (Don't flag pre-existing file
       sizes — focus on what this change contributed.)
 
+    Answer each item above with file:line evidence, not a bare yes or no.
+    An unsupported "yes" is not a review.
+
     ## Calibration
 
     Categorize issues by actual severity. Not everything is Critical.