Initial release: MCP server enforcing Worker-Reviewer loop

Diligence prevents AI agents from shipping quick fixes that break things
by enforcing a research-propose-verify loop before any code changes.

Key features:
- Worker sub-agent researches and proposes with file:line citations
- Reviewer sub-agent independently verifies claims by searching codebase
- Iterates until approved (max 5 rounds)
- Loads project-specific context from .claude/CODEBASE_CONTEXT.md
- State persisted across sessions

Validated on production codebase: caught architectural mistake (broker
subscriptions on client-side code) that naive agent would have shipped.

test/scenarios/index.json

@@ -0,0 +1,21 @@
+{
+  "scenarios": [
+    {
+      "id": "blocking-voice",
+      "file": "blocking-voice.json",
+      "difficulty": "medium",
+      "tags": ["blocking", "voice", "broker-events"]
+    },
+    {
+      "id": "permission-cache",
+      "file": "permission-cache.json",
+      "difficulty": "medium",
+      "tags": ["cache", "permissions", "broker-events"]
+    }
+  ],
+  "metadata": {
+    "version": "1.0.0",
+    "fixture_path": "../fixture",
+    "description": "Test scenarios for diligence MCP server"
+  }
+}