diff --git a/plans/0000-roadmap.md b/plans/0000-roadmap.md
index b3ff259..c4d49f2 100644
--- a/plans/0000-roadmap.md
+++ b/plans/0000-roadmap.md
@@ -83,18 +83,27 @@ the real design happens. The blurbs here stay deliberately loose.
 - [x] **Phase 5: Rule lookup.** A tool that looks up entries in the rules
   layer by case-insensitive keywords, nothing smarter. *You can now:
   watch the DM quote the actual rule.*
-  ([0007](0007-knowledge-mount.md))
-- [ ] **Phase 6: The context stack.** Rules, world, and player knowledge
+  ([0007](completed/0007-knowledge-mount.md))
+- [ ] **Phase 6: Streaming markdown.** The DM speaks markdown and the
+  transcript prints it raw. A renderer that styles the text as it
+  streams, token by token, instead of waiting for a finished block.
+  *You can now: read the DM's words styled, not asterisked.*
+- [ ] **Phase 7: DM prompting.** The first real tuning pass against
+  live sessions, and the DM-versus-player knowledge line: secrets from
+  lore stay behind the screen until the player earns them, and the DM
+  stops narrating its own tool use. *You can now: meet Mother Uldra
+  without being told what she is.*
+- [ ] **Phase 8: The context stack.** Rules, world, and player knowledge
   layered into each turn. The push/pull split gets decided here: what the
   DM always sees versus what it looks up. *You can now: watch the DM
   remember the world from turn to turn.*
-- [ ] **Phase 7: Persistence.** Worlds and players as files on disk.
+- [ ] **Phase 9: Persistence.** Worlds and players as files on disk.
   Character sheet, campaign log, session state. *You can now: quit, come
   back tomorrow, and pick up where you left off.*
-- [ ] **Phase 8 and beyond: ideas that have to earn it.** Character
+- [ ] **Phase 10 and beyond: ideas that have to earn it.** Character
   creation, combat and initiative, background world motion, advancement,
   name generation. Each one starts as a conversation, not a commitment.
 
-Phases 6 and 7 might swap or blur together; building context on in-memory
+Phases 8 and 9 might swap or blur together; building context on in-memory
 state first seemed simpler, but if it feels backwards when we get there,
 we'll flip them. We'll reorder any of this when we have a reason to.
diff --git a/plans/0007-knowledge-mount.md b/plans/completed/0007-knowledge-mount.md
similarity index 100%
rename from plans/0007-knowledge-mount.md
rename to plans/completed/0007-knowledge-mount.md