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.

package.json

@@ -0,0 +1,21 @@
+{
+  "name": "@strikt/diligence",
+  "version": "0.1.0",
+  "description": "MCP server enforcing diligent code changes through worker-reviewer loop",
+  "type": "module",
+  "main": "index.mjs",
+  "bin": {
+    "diligence": "./index.mjs"
+  },
+  "scripts": {
+    "test": "node test/run-tests.mjs --workflow && node test/run-tests.mjs --mock",
+    "test:workflow": "node test/run-tests.mjs --workflow",
+    "test:mock": "node test/run-tests.mjs --mock",
+    "test:dry-run": "node test/dry-run.mjs"
+  },
+  "dependencies": {
+    "@modelcontextprotocol/sdk": "^0.5.0"
+  },
+  "keywords": ["mcp", "claude", "code-review", "diligence"],
+  "license": "MIT"
+}