Summary

Add a reflexion plugin that implements self-refinement techniques based on academic research. This plugin introduces feedback and refinement loops to improve output quality.

Features

• /reflexion:reflect - Self-refinement with complexity triage (Quick/Standard/Deep paths)
• /reflexion:critique - Multi-agent review with 3 specialized judges
• /reflexion:memorize - CLAUDE.md context curation using Agentic Context Engineering

Scientific Foundation

Based on peer-reviewed research demonstrating 8-21% improvement in output quality:

• Self-Refine - Iterative refinement
• Reflexion - Self-reflection for agents
• Agentic Context Engineering - Memory updates (10.6% improvement)

Files Changed

plugins/reflexion/
├── .claude-plugin/plugin.json   # Plugin manifest
├── README.md                    # Documentation
└── commands/
    ├── reflect.md               # Self-refinement command
    ├── critique.md              # Multi-agent review command
    └── memorize.md              # Memory consolidation command

Test Plan

• Verify plugin.json is valid JSON
• Verify all commands have correct frontmatter
• Test /reflexion:reflect command execution
• Test /reflexion:critique command execution
• Test /reflexion:memorize command execution

Closes #64