feat(rules): always_on rulebook flag + Scribe-first prompt

Adds rulebooks.always_on (migration 0058) and a new list_always_on_rules
MCP tool so a session-start eager pull can fetch standing rules without
needing an active-project notion. Updates _INSTRUCTIONS so Claude calls
the new tool at session start and codifies engineering rules in Scribe
rather than CLAUDE.md / auto-memory.

Seeds FabledSword family rulebook to always_on=true on migrate, matching
its design role as the cross-project standards rulebook.

Frontend: badge in RulebookListPane for always-on rulebooks; toggle in
RulebookDetailPane header bound to a new toggleAlwaysOn store action.

This is S1+S2 of the rules-consolidation plan (Scribe task #508). S3
(project-scoped rules) and S4 (enter_project handshake) follow.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/fabledassistant/mcp/server.py

@@ -39,14 +39,21 @@ Mechanics:
   "not set".
 
 Scribe maintains a Rulebook system (Rulebook -> Topic -> Rule). Rules carry
-an actionable statement plus optional Why and How-to-apply context. When you
-start work on a project, get_project(id) returns applicable_rules (the rules
-from rulebooks the project subscribes to) and subscribed_rulebooks. Consult
-these before making decisions about workflow, conventions, or scope. Full
-text (Why / How-to-apply) is available via get_rule(id). You may create new
-rules via create_rule when you notice a pattern worth codifying — coordinate
-with the operator on whether it belongs in an existing rulebook+topic or a
-new one.
+an actionable statement plus optional Why and How-to-apply context. At the
+start of any session that touches Scribe, call list_always_on_rules() to
+load the standing rules — treat them as binding. When you also have a project
+in scope, get_project(id) returns applicable_rules (rules from rulebooks the
+project subscribes to) and subscribed_rulebooks; consult those too. Full text
+(Why / How-to-apply) is available via get_rule(id).
+
+Engineering and workflow rules live in Scribe. When you notice a pattern
+worth codifying, call create_rule. Do NOT add new engineering rules to
+CLAUDE.md or to ~/.claude/.../memory/feedback_*.md — those stores are
+reserved for facts about the user (preferences, role, communication style)
+and codebase onboarding pointers, respectively. Before 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 an existing
+rulebook+topic or a new one.
 
 Plans are tasks with kind=plan, and Scribe is the canonical home for them.
 When you begin non-trivial work, call start_planning(project_id, title) FIRST —

src/fabledassistant/mcp/tools/rulebooks.py

@@ -54,14 +54,26 @@ async def create_rulebook(title: str, description: str = "") -> dict:
 
 async def update_rulebook(
     rulebook_id: int, title: str = "", description: str = "",
+    always_on: bool | None = None,
 ) -> dict:
-    """Update an existing rulebook. Only non-empty fields are changed."""
+    """Update an existing rulebook. Only non-empty fields are changed.
+
+    Args:
+        rulebook_id: Rulebook to update.
+        title: New title. Empty string leaves unchanged.
+        description: New description. Empty string leaves unchanged.
+        always_on: When True, rules in this rulebook are loaded at session
+            start by list_always_on_rules regardless of project context.
+            Pass None to leave unchanged.
+    """
     uid = current_user_id()
     fields: dict = {}
     if title:
         fields["title"] = title
     if description:
         fields["description"] = description
+    if always_on is not None:
+        fields["always_on"] = always_on
     rb = await rulebooks_svc.update_rulebook(rulebook_id, uid, **fields)
     if rb is None:
         raise ValueError(f"rulebook {rulebook_id} not found")
@@ -200,6 +212,28 @@ async def list_rules(
     }
 
 
+async def list_always_on_rules() -> dict:
+    """Return all rules from rulebooks flagged always_on for the current user.
+
+    Call this at session start. Treat the returned rules as binding for the
+    session — they apply regardless of which project (if any) is in scope.
+    Pair with get_project(id).applicable_rules when working on a specific
+    project to also load that project's subscription-derived rules.
+    """
+    uid = current_user_id()
+    rules = await rulebooks_svc.list_always_on_rules(uid)
+    return {
+        "rules": [
+            {
+                "id": r.id, "title": r.title, "statement": r.statement,
+                "topic_id": r.topic_id,
+            }
+            for r in rules
+        ],
+        "total": len(rules),
+    }
+
+
 async def get_rule(rule_id: int) -> dict:
     """Fetch a rule by id — full statement + why + how_to_apply."""
     uid = current_user_id()
@@ -302,7 +336,7 @@ def register(mcp) -> None:
     for fn in (
         list_rulebooks, get_rulebook, create_rulebook, update_rulebook, delete_rulebook,
         list_topics, create_topic, update_topic, delete_topic,
-        list_rules, get_rule, create_rule, update_rule, delete_rule,
+        list_rules, list_always_on_rules, get_rule, create_rule, update_rule, delete_rule,
         subscribe_project_to_rulebook, unsubscribe_project_from_rulebook,
     ):
         mcp.tool(name=fn.__name__)(fn)