claude-reflect

Claude Reflect - Self-Learning System

A two-stage system that helps Claude Code learn from user corrections.

How It Works

Stage 1: Capture (Automatic) Hooks detect correction patterns ("no, use X", "actually...", "use X not Y") and queue them to ~/.claude/learnings-queue.json.

Stage 2: Process (Manual) User runs /reflect to review and apply queued learnings to CLAUDE.md files.

Available Commands

When to Remind Users

Remind users about /reflect when:

• They complete a feature or meaningful work unit
• They make corrections you should remember for future sessions
• They explicitly say "remember this" or similar
• Context is about to compact and queue has items

Correction Detection Patterns

High-confidence corrections:

• Tool rejections (user stops an action with guidance)
• "no, use X" / "don't use Y"
• "actually..." / "I meant..."
• "use X not Y" / "X instead of Y"
• "remember:" (explicit marker)

CLAUDE.md Destinations

• ~/.claude/CLAUDE.md - Global learnings (model names, general patterns)
• ./CLAUDE.md - Project-specific learnings (conventions, tools, structure)

Example Interaction

User: no, use gpt-5.1 not gpt-5 for reasoning tasks
Claude: Got it, I'll use gpt-5.1 for reasoning tasks.

[Hook captures this correction to queue]

User: /reflect
Claude: Found 1 learning queued. "Use gpt-5.1 for reasoning tasks"
        Scope: global
        Apply to ~/.claude/CLAUDE.md? [y/n]