diff --git a/docs/current-state.md b/docs/current-state.md
index 2701a25..576869c 100644
--- a/docs/current-state.md
+++ b/docs/current-state.md
@@ -21,9 +21,9 @@ now includes a first curated ingestion batch for the active projects.
   - Phase 7
 - partial
   - Phase 4
+  - Phase 8
 - not started
   - Phase 6
-  - Phase 8
   - Phase 9
   - Phase 10
   - Phase 11
diff --git a/docs/master-plan-status.md b/docs/master-plan-status.md
index 68fc60f..ed6a53c 100644
--- a/docs/master-plan-status.md
+++ b/docs/master-plan-status.md
@@ -13,30 +13,30 @@ read-only additive mode.
 
 ### Completed
 
-- Phase 0 — Foundation
-- Phase 0.5 — Proof of Concept
-- Phase 1 — Ingestion
+- Phase 0 - Foundation
+- Phase 0.5 - Proof of Concept
+- Phase 1 - Ingestion
 
 ### Baseline Complete
 
-- Phase 2 — Memory Core
-- Phase 3 — Retrieval
-- Phase 5 — Project State
-- Phase 7 — Context Builder
+- Phase 2 - Memory Core
+- Phase 3 - Retrieval
+- Phase 5 - Project State
+- Phase 7 - Context Builder
 
 ### Partial
 
-- Phase 4 — Identity / Preferences
+- Phase 4 - Identity / Preferences
+- Phase 8 - OpenClaw Integration
 
 ### Not Yet Complete In The Intended Sense
 
-- Phase 6 — AtoDrive
-- Phase 8 — OpenClaw Integration
-- Phase 9 — Reflection
-- Phase 10 — Write-back
-- Phase 11 — Multi-model
-- Phase 12 — Evaluation
-- Phase 13 — Hardening
+- Phase 6 - AtoDrive
+- Phase 9 - Reflection
+- Phase 10 - Write-back
+- Phase 11 - Multi-model
+- Phase 12 - Evaluation
+- Phase 13 - Hardening
 
 ## What Is Real Today
 
@@ -56,6 +56,9 @@ read-only additive mode.
 - conservative Trusted Project State for those active projects
 - first operational backup foundation for SQLite + project registry
 - implementation-facing architecture notes for future engineering knowledge work
+- first organic routing layer in OpenClaw via:
+  - `detect-project`
+  - `auto-context`
 
 ## Now
 
@@ -116,8 +119,8 @@ These remain intentionally deferred.
 
 The next sensible implementation threshold for the engineering ontology work is:
 
-- after the current ingestion, retrieval, registry, OpenClaw helper, and backup
-  baseline feels boring and dependable
+- after the current ingestion, retrieval, registry, OpenClaw helper, organic
+  routing, and backup baseline feels boring and dependable
 
 Until then, the architecture docs should shape decisions, not force premature
 schema work.