diff --git a/scripts/install.sh b/scripts/install.sh
index 8ba0a6a..3a758c7 100644
--- a/scripts/install.sh
+++ b/scripts/install.sh
@@ -64,6 +64,12 @@ if [[ "${TARGET}" == "${HOME}" ]]; then
 	else
 		warn "skills: no systemd user session; skipped the kvb-dream notification timer."
 	fi
+	if command -v codebase-memory-mcp &>/dev/null; then
+		log "skills: auto-indexing every repository a session opens into the code graph"
+		codebase-memory-mcp config set auto_index true
+	else
+		warn "skills: codebase-memory-mcp not installed; the code graph stays off (see kvb-agent-optimize)."
+	fi
 fi
 
 log "skills: done. Restart your agent to load the skills."
diff --git a/skills/kvb-agent-optimize/SKILL.md b/skills/kvb-agent-optimize/SKILL.md
index 3a53e4c..360d2ab 100644
--- a/skills/kvb-agent-optimize/SKILL.md
+++ b/skills/kvb-agent-optimize/SKILL.md
@@ -33,8 +33,12 @@ installed, and the state of the shared snapshot
   claude plugin install codebase-memory@codebase-memory
   ```
 
-- **Index** with the MCP tool `index_repository` on the repository path, then
-  `check_index_coverage`; every file kind it leaves out is a finding.
+- **Index**: once installed, the skills repository's `make install` switches
+  `auto_index` on, so every repository a session opens is indexed and
+  watched; every skill that explores code asks the graph first. Check it with
+  `index_status`, index by hand with `index_repository` only where it is
+  missing, then `check_index_coverage`; every file kind it leaves out is a
+  finding.
 - **Snapshot**: ask whether the repository shares its graph. Shared: run
   `index_repository` with `persistence: true` and commit
   `.codebase-memory/graph.db.zst` at a fixed cadence (every commit of it adds