diff --git a/src/fabledassistant/mcp/server.py b/src/fabledassistant/mcp/server.py
index 79de92b..d6b1a5b 100644
--- a/src/fabledassistant/mcp/server.py
+++ b/src/fabledassistant/mcp/server.py
@@ -68,6 +68,19 @@ creating a rule, call list_always_on_rules and list_rules(project_id=...) to
 avoid duplicates. Coordinate with the operator on whether a new rule belongs
 in a project, an existing rulebook+topic, or a new rulebook.
 
+That boundary cuts the other way too. Because rules are pull-only, a fresh
+session won't reach for them unless its always-loaded context says to. So
+when the current project subscribes to a rulebook (enter_project /
+get_project reports subscribed_rulebooks), make sure the host's persistent
+memory — the CLAUDE.md / AGENTS.md / ~/.claude memory the client loads at
+startup — carries a short pointer: that the engineering and workflow rules
+for this work live in Scribe and must be loaded via list_always_on_rules (or
+enter_project when a project is in scope), plus a one-line note of what the
+current project is and what is in flight. Add or refresh that pointer when
+it's missing or stale; never copy the rules' content into memory — the
+pointer plus project context is the whole job. This is what lets the next
+session reach for Scribe instead of trusting a stale local copy.
+
 When you are working on a specific project, call enter_project(project_id)
 ONCE at session start (or whenever the active project changes). It returns the
 project, its applicable_rules + project_rules + subscribed_rulebooks, milestone