diff --git a/CLAUDE.md b/CLAUDE.md
index 24d576e..cb75d76 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -77,6 +77,16 @@ brings that output straight back:
 `diversify()` caps each strategy at ~28% of the list. Without it the top 20 came
 back as eighteen coinages — raw score ranking clumps badly.
 
+## Paging appends — never re-look-up
+
+36 names per page (`NAME_COUNT`), and **"Show me more" appends**: Finder passes the
+names already on screen as `exclude`, and `generateNames` drops them *before* ranking.
+A new seed alone mostly reshuffles the same pool — that was the old behaviour and it
+re-checked domains the visitor had already seen. Two invariants: an append reuses the
+current `runId` (so earlier cards keep resolving) and only looks up the NEW domains;
+changing keywords/style/extensions starts a fresh list. When the pool is exhausted the
+UI says so rather than silently returning nothing.
+
 ## Shared OTM widgets need Tailwind
 
 The bottom-right feedback chat-pop is `SuggestionLightbulb` from