Extract outercourse role graph wording

docs/prompt-architecture-improvement-plan.md

@@ -102,6 +102,9 @@ Already isolated:
 - hardcore configured-cast role graph generation lives in
   `hardcore_role_graphs.py`; `prompt_builder.py` selects item/axis metadata and
   then asks that module for the source role graph.
+- outercourse-specific role graph wording has started moving into action-family
+  modules; `hardcore_role_outercourse.py` owns boobjob, testicle-sucking,
+  penis-licking, handjob, and footjob body geometry.
 - camera-scene prose and coworking composition adaptation live in
   `scene_camera_adapters.py`; `prompt_builder.py` still owns camera config
   parsing and row mutation.
@@ -358,7 +361,7 @@ Medium-term:
 
 1. Split `__init__.py` node classes by family after behavior is covered by smoke
    checks.
-2. Split the internals of `hardcore_role_graphs.py` by action family once more
-   generated edge cases are covered by smoke fixtures.
+2. Continue splitting the internals of `hardcore_role_graphs.py` by action
+   family once generated edge cases are covered by smoke fixtures.
 3. Add more route-level smoke fixtures for generated edge cases that are not
    covered by the current static Krea/SDXL/caption metadata fixtures.