feat: implement CI (Continuous Intelligence) autonomous engineering harness

Implements the full PRD for CI - a fully autonomous AI-driven software
engineering harness derived from Learnship's architecture.

Core components:
- CI Orchestrator agent with autonomous pipeline (SPECIFY → CLARIFY →
  RESEARCH → PLAN → EXECUTE → VERIFY → COMPLETE)
- Decision Engine with confidence thresholds (high/medium/low)
- Clarify Phase with question budget and default acceptance
- Escalation Protocol with timeout auto-proceed
- Audit Trail system (.ci/audit/) for post-hoc review
- Error Recovery with retry, plan revision, and rollback

18 agents (all Learnship agents + Orchestrator):
- Autonomous behavioral modifications per PRD §7.1
- Agent registry with factory pattern

11 CLI commands:
- ci init, ci run, ci quick, ci debug, ci verify
- ci review, ci status, ci audit, ci clarify
- ci rollback, ci ship

4-layer verification system:
- Structural, Behavioral, Security, Code Quality

3 autonomy levels: full, supervised, guided
Compatible with Learnship artifact schemas (.planning/)

src/agents/base.ts

@@ -0,0 +1,36 @@
+export interface AgentResult {
+  success: boolean;
+  output: string;
+  artifacts_created: string[] | number;
+  decisions: number;
+  escalations: number;
+  duration_ms: number;
+  error?: string;
+}
+
+export interface AgentContext {
+  project_path: string;
+  phase: number;
+  stage: string;
+  specification: string;
+  config_path: string;
+}
+
+export abstract class BaseAgent {
+  abstract readonly name: string;
+  abstract readonly description: string;
+
+  abstract execute(context: AgentContext): Promise<AgentResult>;
+
+  protected log(message: string): void {
+    console.log(`[${this.name}] ${message}`);
+  }
+
+  protected warn(message: string): void {
+    console.warn(`[${this.name}] ⚠ ${message}`);
+  }
+
+  protected error(message: string): void {
+    console.error(`[${this.name}] ✗ ${message}`);
+  }
+}