fix(curator): default cycle is every 7 days, not 24 hours

Weekly is closer to how skill churn actually works — most agent-created
skills don't change multiple times per day, so a daily review is pure
cost without benefit. Bumping the default to 7 days reduces aux-model
spend while still catching drift and staleness on the timescales that
matter (30d stale, 90d archive).

Changes:
- DEFAULT_INTERVAL_HOURS: 24 -> 168 (7 days)
- config.yaml default: interval_hours: 24 -> 24 * 7
- CLI status line renders as '7d' when interval is a whole-day multiple
- Test `test_old_run_eligible` decoupled from the exact default: it now
  uses 2 * get_interval_hours() so future tweaks don't break it

hermes_cli/config.py

@@ -927,8 +927,8 @@ DEFAULT_CONFIG = {
     # See `hermes curator status` for the last run summary.
     "curator": {
         "enabled": True,
-        # How long to wait between curator runs (hours).
-        "interval_hours": 24,
+        # How long to wait between curator runs (hours).  Default: 7 days.
+        "interval_hours": 24 * 7,
         # Only run when the agent has been idle at least this long (hours).
         "min_idle_hours": 2,
         # Mark a skill as "stale" after this many days without use.

hermes_cli/curator.py

@@ -55,7 +55,12 @@ def _cmd_status(args) -> int:
     print(f"  runs:           {runs}")
     print(f"  last run:       {_fmt_ts(last_run)}")
     print(f"  last summary:   {summary}")
-    print(f"  interval:       every {curator.get_interval_hours()}h")
+    _ih = curator.get_interval_hours()
+    _interval_label = (
+        f"{_ih // 24}d" if _ih % 24 == 0 and _ih >= 24
+        else f"{_ih}h"
+    )
+    print(f"  interval:       every {_interval_label}")
     print(f"  stale after:    {curator.get_stale_after_days()}d unused")
     print(f"  archive after:  {curator.get_archive_after_days()}d unused")