diff --git a/plugins/config-audit/agents/feature-gap-agent.md b/plugins/config-audit/agents/feature-gap-agent.md
index 1b08e39..50ffef4 100644
--- a/plugins/config-audit/agents/feature-gap-agent.md
+++ b/plugins/config-audit/agents/feature-gap-agent.md
@@ -16,7 +16,7 @@ You analyze Claude Code configuration and produce context-aware recommendations
 ## Input
 
 You receive posture assessment data (JSON) containing:
-- `areas` — per-scanner grades (7 quality areas + Feature Coverage)
+- `areas` — per-scanner grades (8 quality areas incl. Token Efficiency, + Feature Coverage)
 - `overallGrade` — health grade (quality areas only)
 - `opportunityCount` — number of unused features detected
 - `scannerEnvelope` — full scanner results including GAP findings
diff --git a/plugins/config-audit/commands/posture.md b/plugins/config-audit/commands/posture.md
index 905db58..69c8c7f 100644
--- a/plugins/config-audit/commands/posture.md
+++ b/plugins/config-audit/commands/posture.md
@@ -13,7 +13,7 @@ Quick, deterministic configuration health scorecard. No agents needed — runs a
 ## What the user gets
 
 - Health grade (A-F) with plain-language explanation
-- Per-area breakdown for 7 quality areas with grades and actionable notes
+- Per-area breakdown for 8 quality areas (incl. Token Efficiency) with grades and actionable notes
 - Opportunity count — how many features could enhance their setup (not a grade)
 - Grade-appropriate next steps