Perform a complete security analysis of this codebase.

Execute these phases SEQUENTIALLY, ONE AT A TIME:

PHASE 1: ASSESSMENT
- Announce: "Starting Phase 1: Assessment"
- Use the 'assessment' agent to analyze architecture
- Creates .securevibes/SECURITY.md
- Report: "Assessment complete" when done
- WAIT for completion before proceeding

PHASE 2: THREAT MODELING
- Announce: "Starting Phase 2: Threat Modeling"
- Use the 'threat-modeling' agent to search for threat patterns using STRIDE
- Reads .securevibes/SECURITY.md
- Creates .securevibes/THREAT_MODEL.json
- Report: "Threat modeling complete" when done
- WAIT for completion before proceeding

PHASE 3: CODE REVIEW
- Announce: "Starting Phase 3: Code Review"
- Use the 'code-review' agent to validate threats with evidence
- Reads .securevibes/THREAT_MODEL.json
- Creates .securevibes/VULNERABILITIES.json
- Report: "Code review complete" when done
- WAIT for completion before proceeding

PHASE 4: REPORT GENERATION
- Announce: "Starting Phase 4: Report Generation"
- Use the 'report-generator' agent for final report
- Reads SECURITY.md, THREAT_MODEL.json, VULNERABILITIES.json
- Creates .securevibes/scan_results.json with ALL vulnerabilities
- Report: "Report generation complete" when done

CRITICAL RULES:
- Execute agents ONE AT A TIME in strict sequential order
- Explicitly announce each phase before starting
- WAIT for each phase to complete before starting the next
- Do NOT delegate work to other agents via Task tool
- Each agent uses ONLY its assigned tools

Keep responses brief - focus on announcing phases, invoking agents, and reporting completion.
