learn

# /learn — Behavioral Correction When a user corrects a mistake, `/learn` diagnoses which behavioral surface caused it and applies a minimal, targeted fix. ## When to Use - User corrects agent behavior ("no, don't do that", "you should always...", "stop doing X") - Agent made a mistake that should never recur - User explicitly invokes `/learn` - A pattern of repeated errors suggests a missing behavioral rule ## How It Works This is an **interactive skill**. The user invokes `/learn` directly, and the agent runs in the foreground, conversing with the user throughout. ## Flow 1. **Analyze the mistake:** What went wrong? Read the conversation context, recent changes, and relevant code to understand the error. 2. **Determine root cause:** Why did the agent behave this way? Missing rule? Stale convention? Wrong default? 3. **Diagnose the surface:** Which behavioral surface needs to change? (See Writable Surfaces below.) 4. **Propose minimal fix:** Enter native plan mode. Show exactly which file will change, what content will be added/modified, and why. One change per learning — never batch. 5. **Apply with approval:** User must approve before any write. Apply the change. Confirm what was learned. 6. **Save to memory:** Write the learning as a feedback memory in `.claude/memory/` so Claude native memory retains it across sessions. ## Writable Surfaces The learn agent diagnoses which surface needs the fix: | Surface | Path | What It Controls | |---------|------|------------...