Issue Description

Labels: enhancement, agents, accessibility, compliance, size: small

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.

This specific issue focuses on the pre-PR compliance validation phase, adding the Responsible AI agent that ensures accessibility (WCAG 2.1) and bias prevention before code reaches @pr-review.

Overview

Integrate the Responsible AI agent to provide accessibility compliance (WCAG 2.1), bias prevention, and ethical code development checks before PR submission.

User Story

As a developer on the HVE Core team, I want automated accessibility and bias validation during development, so that I catch compliance issues early when fixes are small rather than during PR review or after deployment.

Context

• Problem: Compliance issues found late = expensive retrofits and delayed releases
• Value Add: Responsible AI practices and Accessibility built-in from day one, 80% faster fixes (caught during development)
• Integration Point: Post-implementation quality gate before existing @pr-review

Source Repository

• Engineering Team Agents: https://github.com/niksacdev/engineering-team-agents
• Responsible AI Agent: https://github.com/niksacdev/engineering-team-agents/blob/main/.claude/agents/responsible-ai-code.md
• Original Proposal: feat(agents): Engineering Agents Integration #63

Acceptance Criteria

• Responsible AI agent works in Claude Code (.claude/agents/)
• Responsible AI agent works in GitHub Copilot (.github/agents/ and .github/chatmodes/)
• AGENTS.md includes agent in universal format
• Agent creates RAI-ADRs (Responsible AI Architecture Decision Records) in docs/responsible-ai/
• RAI-ADR template added to docs/templates/
• Agent performs WCAG 2.1 compliance checks
• Agent detects AI/ML bias patterns (OWASP LLM/ML context)
• Agent validates privacy controls and data collection
• 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/responsible-ai/RAI-ADR-[number]-[title].md
  • docs/responsible-ai/responsible-ai-evolution.md
  • docs/templates/responsible-ai-adr-template.md
• Compliance Checks: WCAG 2.1 AA, keyboard accessibility, screen reader compatibility, color contrast, privacy controls
• Security Integration: OWASP LLM Top 10 awareness for AI systems

Implementation Phases

Phase 1: Port Agent

1. Adapt responsible-ai-code.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/responsible-ai/ directory
2. Port RAI-ADR template
3. Create responsible-ai-evolution.md tracking file
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 RAI-ADR creation workflow
4. Test accessibility check patterns
5. Validate backward compatibility

Definition of Done

• Agent works in all three formats
• RAI-ADR template functional
• Accessibility checks validated (keyboard, screen reader, contrast)
• Bias detection patterns working
• Integration before @pr-review documented
• README.md updated with accessibility workflow
• All existing tests pass
• No breaking changes

Dependencies

• None (independent implementation)

Related Documentation

• Source Repository: https://github.com/niksacdev/engineering-team-agents
• Responsible AI Agent: https://github.com/niksacdev/engineering-team-agents/blob/main/.claude/agents/responsible-ai-code.md
• Issue feat(agents): Engineering Agents Integration #63: feat(agents): Engineering Agents Integration #63
• WCAG 2.1 Standards: https://www.w3.org/WAI/WCAG21/quickref/
• OWASP LLM Top 10: https://owasp.org/www-project-top-10-for-large-language-model-applications/

Additional Context

No response