Issue Description

Labels: enhancement, agents, architecture, documentation, size: medium

Epic: #63 - Engineering Agents Integration

Related Issues: Part of breaking down #63 into focused implementation tasks

Epic Context

This issue is part of the larger Engineering Agents Integration epic (#63), which aims to integrate 6 collaborative engineering agents from the engineering-team-agents repository into HVE Core. The epic provides multi-platform support (GitHub Copilot + Claude Code + AGENTS.md) while enhancing the existing research → plan → implement workflow with quality gates at strategic points.

Overview

Integrate the System Architecture Reviewer agent to create Architecture Decision Records (ADRs) and preserve institutional knowledge after research and before planning.

User Story

As a developer on the HVE Core team, I want automated architecture documentation and decision tracking, so that technical decisions are preserved and new team members don't repeat past mistakes or debates.

Context

• Current Gap: Technical decisions lost over time, architecture debates repeated
• Problem: Institutional knowledge exists only in people's heads, new developers lack context
• Value Add: Zero repeated architecture debates, preserved decision rationale, scalable team knowledge
• Integration Point: Post-research documentation gate, provides context for @task-planner

Source Repository

• Engineering Team Agents: https://github.com/niksacdev/engineering-team-agents
• Architecture Reviewer Agent: https://github.com/niksacdev/engineering-team-agents/blob/main/.claude/agents/system-architecture-reviewer.md
• ADR Template: https://github.com/niksacdev/engineering-team-agents/tree/main/docs/templates
• Original Proposal: feat(agents): Engineering Agents Integration #63

Acceptance Criteria

• Architecture Reviewer agent works in Claude Code (.claude/agents/)
• Architecture Reviewer agent works in GitHub Copilot (.github/agents/ and .github/chatmodes/)
• AGENTS.md includes agent in universal format
• Agent creates ADRs in docs/architecture/
• ADR template added to docs/templates/
• Agent applies Microsoft Well-Architected Framework (AI-specific pillars)
• Agent applies OWASP security patterns (Top 10, LLM, ML)
• Agent implements Zero Trust architecture principles
• Agent can consult Code Reviewer, DevOps, and Product Manager
• Agent follows HVE Core conventions
• All existing HVE Core tests pass

Technical Requirements

• Platform Support: Claude Code, GitHub Copilot (native + chatmodes), universal AGENTS.md
• Documentation Structure:
  • docs/architecture/ADR-[number]-[title].md
  • docs/templates/adr-template.md
• Frameworks Applied:
  • Microsoft Well-Architected Framework (AI pillars)
  • OWASP Top 10 Architecture
  • OWASP LLM Security Architecture
  • OWASP ML Security Architecture
  • Zero Trust principles
• Decision Trees: Database choice, AI architecture, deployment patterns, caching strategies

Implementation Phases

Phase 1: Port Agent

1. Adapt system-architecture-reviewer.md from source repository
2. Create Claude version (.claude/agents/)
3. Create GitHub native version (.github/agents/)
4. Create GitHub chatmode version (.github/chatmodes/)
5. Add agent to AGENTS.md

Phase 2: Documentation Setup

1. Create docs/architecture/ directory
2. Port ADR template
3. Add framework reference documentation
4. Add cross-references to existing instructions

Phase 3: Integration & Testing

1. Test agent in Claude Code
2. Test agent in GitHub Copilot
3. Validate ADR creation workflow
4. Test cross-agent collaboration (Architecture → Code Reviewer)
5. Validate backward compatibility

Definition of Done

• Agent works in all three formats
• ADR template functional and validated
• Architecture frameworks properly applied
• Cross-agent collaboration working (can consult other specialists)
• Integration with @task-planner documented
• README.md updated with architecture workflow
• All existing tests pass
• No breaking changes

Dependencies

• None (independent implementation)

Related Documentation

• Source Repository: https://github.com/niksacdev/engineering-team-agents
• Architecture Agent: https://github.com/niksacdev/engineering-team-agents/blob/main/.claude/agents/system-architecture-reviewer.md
• Issue feat(agents): Engineering Agents Integration #63: feat(agents): Engineering Agents Integration #63
• Microsoft Well-Architected Framework: https://learn.microsoft.com/azure/well-architected/
• OWASP Top 10: https://owasp.org/www-project-top-ten/
• OWASP LLM Top 10: https://owasp.org/www-project-top-10-for-large-language-model-applications/
• OWASP ML Security: https://owasp.org/www-project-machine-learning-security-top-10/

Additional Context

No response