feat: initial Claude Code configuration scaffold

Comprehensive Claude Code guidance system with:

- 5 agents: tdd-guardian, code-reviewer, security-scanner, refactor-scan, dependency-audit
- 18 skills covering languages (Python, TypeScript, Rust, Go, Java, C#),
  infrastructure (AWS, Azure, GCP, Terraform, Ansible, Docker/K8s, Database, CI/CD),
  testing (TDD, UI, Browser), and patterns (Monorepo, API Design, Observability)
- 3 hooks: secret detection, auto-formatting, TDD git pre-commit
- Strict TDD enforcement with 80%+ coverage requirements
- Multi-model strategy: Opus for planning, Sonnet for execution (opusplan)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.claude/settings.json

@@ -0,0 +1,52 @@
+{
+  "model": "opusplan",
+  "permissions": {
+    "allow": [
+      "Bash(pytest:*)",
+      "Bash(npm test:*)",
+      "Bash(cargo test:*)",
+      "Bash(ruff:*)",
+      "Bash(terraform plan:*)",
+      "Bash(terraform validate:*)",
+      "Bash(ansible-playbook:--check*)",
+      "Bash(git status:*)",
+      "Bash(git diff:*)",
+      "Bash(git log:*)"
+    ],
+    "deny": [
+      "Bash(rm -rf /*)",
+      "Bash(terraform apply:--auto-approve*)",
+      "Bash(terraform destroy:*)",
+      "Bash(git push:--force*)",
+      "Bash(git reset:--hard*)"
+    ]
+  },
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "~/.claude/hooks/check-secrets.sh"
+          }
+        ]
+      }
+    ],
+    "PostToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "~/.claude/hooks/auto-format.sh"
+          }
+        ]
+      }
+    ]
+  },
+  "env": {
+    "COVERAGE_THRESHOLD": "80",
+    "TDD_STRICT": "true"
+  }
+}