fix(curator): only mark agent-created for background-review sediment (#19621)

Tighten the provenance semantics added in #19618: skills a user asks a
foreground agent to write via skill_manage(create) now stay invisible to
the curator. Only skills the background self-improvement review fork
sediments through skill_manage get the created_by=agent marker.

- tools/skill_provenance.py — new ContextVar module mirroring the
  _approval_session_key pattern: set_current_write_origin / reset /
  get / is_background_review. Default origin is 'foreground'; the
  review fork sets 'background_review'.
- run_agent.py — run_conversation() binds the ContextVar from
  self._memory_write_origin at the top of each call. The review fork
  runs on its own thread (fresh context), so foreground and review
  contexts never cross-contaminate.
- tools/skill_manager_tool.py — skill_manage(action='create') now
  only calls mark_agent_created() when is_background_review(). All
  other cases (foreground create, patch, edit, write_file, delete)
  continue as before.
- tests: test_skill_provenance.py (6 tests covering the ContextVar
  surface), split test_full_create_via_dispatcher into foreground
  vs. review-fork variants, curator status tests now mark-first.

Why: the agent routinely edits existing user skills on the user's
behalf; those writes must never flip provenance. And when a user
explicitly asks the foreground agent to create a skill, that skill
belongs to the user. The curator should only be cleaning up after
its own autonomous sediment from the review nudge loop.

tests/hermes_cli/test_curator_status.py

@@ -114,6 +114,12 @@ def test_status_shows_most_and_least_used_sections(curator_status_env):
     env["make_skill"]("top-dog")
     env["make_skill"]("middling")
     env["make_skill"]("never-used")
+    # Mark all three as agent-created so they enter the curator's catalog.
+    # Under the provenance-marker semantics, skills must be explicitly opted
+    # into curator management (normally via the background-review fork when
+    # it creates a skill through skill_manage).
+    for n in ("top-dog", "middling", "never-used"):
+        env["skill_usage"].mark_agent_created(n)
 
     # Bump use_count differentially. All three counters (use/view/patch) feed
     # into activity_count, so bumping use alone is enough to make activity
@@ -150,7 +156,9 @@ def test_status_hides_most_active_when_all_zero(curator_status_env):
     env = curator_status_env
     env["make_skill"]("a")
     env["make_skill"]("b")
-    # No bumps.
+    # Mark both as agent-created so the catalog lists them. No bumps.
+    env["skill_usage"].mark_agent_created("a")
+    env["skill_usage"].mark_agent_created("b")
 
     out = _capture_status(env["curator_cli"])