Fix TOOL-02: read verifier verdicts with prose around them

The verdict reader matched from the first { to the last } in the whole
reply, so a fenced JSON verdict followed by prose containing a } failed
to parse, counted as FAIL and triggered a rewrite (SAFETY-129, T192).

- Read a ```json fenced block first, then the first balanced {...} that
  parses and has a PASS or FAIL verdict. Braces inside strings are
  ignored.
- An unreadable reply is re-asked once for the JSON only. Still
  unreadable: NOT VERIFIED, "verdict unreadable", handed back to the
  manager with the start of the first reply. No fail counted, no
  resume, no rewrite.
- 10 new tests; each new rule was also broken on purpose and caught.

Version 0.4.5.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MdqPWvuDpbpRvDEdURoAwo

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "model-router",
-  "version": "0.4.4",
+  "version": "0.4.5",
   "description": "Routes each subagent to Haiku, Sonnet or Opus by how well-defined its brief is, verifies dev work below Opus in its own clone on a different model, sends failures back to the same agent then a stronger one, and estimates the savings against Opus.",
   "author": {
     "name": "Glenn Schrooyen"