Ready-to-use behavioral mode files for Claude Code. Copy to ~/.claude/ and reference in your CLAUDE.md.
| Mode | File | Purpose |
|---|---|---|
| Learning | MODE_Learning.md | Just-in-time explanations when techniques are first used |
cp MODE_Learning.md ~/.claude/Add to ~/.claude/CLAUDE.md:
# Behavioral Modes
@MODE_Learning.mdAdd to ~/.claude/FLAGS.md for flag-based activation:
**--learn**
- Trigger: User requests learning mode, "why/how" questions
- Behavior: Enable just-in-time explanations with first-occurrence tracking
**--no-learn**
- Trigger: User wants pure execution without educational offers
- Behavior: Suppress all learning mode offers# Activate for entire session
claude --learn
# Focus on specific domain
claude --learn focus:git
claude --learn focus:architecture
# Batch explanations at task end
claude --learn batchThis guide includes only Learning Mode. For a complete behavioral framework with additional modes, check out SuperClaude:
| Mode | Purpose |
|---|---|
| Orchestration | Smart tool selection, parallel execution optimization |
| Task Management | Hierarchical task tracking with persistent memory |
| Token Efficiency | Symbol-enhanced compression (30-50% token reduction) |
| Learning | Just-in-time skill development (included here) |
SuperClaude also includes:
FLAGS.md— Behavioral flags (--delegate,--learn, etc.) Note:--think/--ultrathinkare cosmetic only since v2.0.67 — thinking is now on by default with Opus 4.5PRINCIPLES.md— Engineering principles (SOLID, DRY, evidence-based)RULES.md— Actionable rules with priority system- MCP server documentation (Context7, Sequential, Serena)
- Guide Section 10.5: SuperClaude Framework — Full documentation
- SuperClaude Repository — Complete framework