fix(issue-23-24): merge review - the environment form of the auto-trust switch reaches the handler; a rate-limited dialog does not hide the next one

Two probes from the merge-side codex review (its report was lost to an API
outage; the probes and their results were recovered from its transcript):

- create_session.sh and resume_session.sh set AUTO_TRUST=1 and then
  exported MAM_AUTO_TRUST from it, so the documented MAM_AUTO_TRUST=0
  without a flag reached handle_startup_dialogs as 1: the operator had
  turned automatic trust off and it stayed on. Now AUTO_TRUST defaults to
  the environment value and an explicit --auto-trust/--no-auto-trust wins.
- _mam_dialog_pick exited on the first dialog inside its resend cooldown
  instead of looking further down the screen, so a skipped (--no-auto-trust)
  or just-answered trust prompt hid the codex update notice below it, which
  the docs say is always answered. It continues to the next dialog now; S5
  and S5b (one send per cooldown, one retry after it) still hold.

Regressions: S6c, S5f (startup path), R3b and C3 (resume/create, env only,
flag over env). Each fails without the fix. The create skill doc names the
environment form and its precedence.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff

.agents/skills/lib.sh

@@ -2952,7 +2952,10 @@ for idx, entry in enumerate(dialogs):
         continue
     last = state.get(idx)
     if last is not None and 0 <= now - last < cooldown:
-        sys.exit(1)
+        # rate-limited: look at the other dialogs on this screen instead of
+        # giving up (merge review, codex probe: a skipped trust prompt or a
+        # freshly answered one used to hide the notice below it)
+        continue
     if kind == "trust" and not auto_trust:
         print("skip|%d|" % idx)
         sys.exit(0)