# Claudette & Beast Mode Version Comparison

## 📊 Size Metrics

| Version | Lines | Words | Est. Tokens | Size vs Original |
|---------|-------|-------|-------------|------------------|
| **claudette-original.md** | 703 | 3,645 | ~4,860 | Baseline (100%) |
| **claudette-auto.md** | 468 | 2,564 | ~3,418 | -30% |
| **claudette-condensed.md** | 370 | 1,949 | ~2,598 | -47% |
| **claudette-compact.md** | 254 | 1,108 | ~1,477 | -70% |
| **beast-mode.md** | 152 | 1,967 | ~2,620 | -46% |

---

## 🎯 Feature Matrix

| Feature | Original | Auto | Condensed | Compact | Beast |
|---------|----------|------|-----------|---------|-------|
| **Core Identity** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Productive Behaviors** | ❌ | ✅ | ✅ | ✅ | ❌ |
| **Anti-Pattern Examples (❌/✅)** | ❌ | ✅ | ✅ | ✅ | ❌ |
| **Execution Protocol** | 5-phase | 3-phase | 3-phase | 3-phase | 10-step |
| **Repository Conservation** | ✅ | ✅ | ✅ | ✅ | ❌ |
| **Dependency Hierarchy** | ✅ | ✅ | ✅ | ✅ | ❌ |
| **Project Type Detection** | ✅ | ✅ | ✅ | ✅ | ❌ |
| **TODO Management** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Segue Management** | ✅ | ✅ | ✅ | ✅ | ❌ |
| **Segue Cleanup Protocol** | ❌ | ✅ | ✅ | ✅ | ❌ |
| **Error Debugging Protocols** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Research Methodology** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Communication Protocol** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Completion Criteria** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Context Drift Prevention** | ❌ | ✅ (Event-driven) | ✅ (Event-driven) | ✅ (Event-driven) | ❌ |
| **Failure Recovery** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Execution Mindset** | ❌ | ✅ | ✅ | ✅ | ❌ |
| **Effective Response Patterns** | ❌ | ✅ | ✅ | ✅ | ❌ |
| **URL Fetching Protocol** | ❌ | ❌ | ❌ | ❌ | ✅ |
| **Memory System** | ❌ | ✅ (Proactive) | ✅ (Proactive) | ✅ (Compact) | ✅ (Reactive) |
| **Git Rules** | ✅ | ✅ | ✅ | ✅ | ✅ |

---

## 🔑 Key Differentiators

| Aspect | Original | Auto | Condensed | Compact | Beast |
|--------|----------|------|-----------|---------|-------|
| **Tone** | Professional | Professional | Professional | Professional | Casual |
| **Verbosity** | High | Medium | Low | Very Low | Low |
| **Structure** | Detailed | Streamlined | Condensed | Minimal | Workflow |
| **Emphasis** | Comprehensive | Autonomous | Efficient | Token-optimal | Research |
| **Target LLM** | GPT-4, Claude Opus | GPT-4, Claude Sonnet | GPT-4 | GPT-3.5, Lower-reasoning | Any |
| **Use Case** | Complex enterprise | Most tasks | Standard tasks | Token-constrained | Research-heavy |
| **Context Drift** | ❌ | ✅ (Event-driven) | ✅ (Event-driven) | ✅ (Event-driven) | ❌ |
| **Optimization Focus** | None | Autonomous execution | Length reduction | Token efficiency | Research workflow |

---

## 💡 Recommended Use Cases

### **claudette-original.md** (703 lines, ~4,860 tokens)
- ✅ Reference documentation
- ✅ Most comprehensive guidance
- ✅ When token count is not a concern
- ✅ Training new agents
- ⚠️ Not optimized for autonomous execution

### **claudette-auto.md** (467 lines, ~3,418 tokens)
- ✅ Most tasks and complex projects
- ✅ Enterprise repositories
- ✅ Long conversations (event-driven context drift prevention)
- ✅ GPT-4 Turbo, Claude Sonnet, Claude Opus
- ✅ Optimized for autonomous execution
- ✅ Proactive memory management (cross-session learning)
- ✅ Most comprehensive guidance

### **claudette-condensed.md** (370 lines, ~2,598 tokens) ⭐ **RECOMMENDED**
- ✅ Standard coding tasks
- ✅ Best balance of features vs token count
- ✅ GPT-4, Claude Sonnet
- ✅ Event-driven context drift prevention
- ✅ Proactive memory management (cross-session learning)
- ✅ 24% smaller than Auto with same core features
- ✅ Ideal for most use cases

### **claudette-compact.md** (254 lines, ~1,477 tokens)
- ✅ Token-constrained environments
- ✅ Lower-reasoning LLMs (GPT-3.5, smaller models)
- ✅ Simple, straightforward tasks
- ✅ Maximum context window for conversation
- ✅ Event-driven context drift prevention (ultra-compact)
- ✅ Compact memory management (minimal token overhead)
- ⚠️ Minimal examples and explanations

### **beast-mode.md** (152 lines, ~2,620 tokens)
- ✅ Research-heavy tasks
- ✅ URL scraping and recursive link following
- ✅ Tasks with provided URLs
- ✅ Casual communication preferred
- ✅ Persistent memory across sessions
- ⚠️ No repository conservation
- ⚠️ No context drift prevention
- ⚠️ Not enterprise-focused

---

## 📈 Token Efficiency vs Features Trade-off

```
Original    ████████████████████ 4,860 tokens | ████████████ Features
Auto        ████████████▌        3,418 tokens | ████████████ Features (+ Memory)
Condensed   ██████████▌          2,598 tokens | ████████████ Features (+ Memory) ⭐
Compact     ██████               1,477 tokens | ███████████  Features (+ Memory)
Beast       ██████████▌          2,620 tokens | ███████      Features (+ Memory)
```

---

## 🎯 Quick Selection Guide

**Choose based on priority:**

1. **Need best balance?** → `claudette-condensed.md` ⭐ **RECOMMENDED**
2. **Need most comprehensive?** → `claudette-auto.md`
3. **Need smallest token count?** → `claudette-compact.md`
4. **Need URL fetching/research?** → `beast-mode.md`
5. **Need reference documentation?** → `claudette-original.md`
6. **All versions now have event-driven context drift prevention!**

---

## 📊 Evolution Timeline

```
claudette-original.md (v1)
    ↓
    ├─→ claudette-auto.md (v5) - Autonomous optimization + context drift + memories
    ↓
claudette-condensed.md (v3)
    ↓
claudette-compact.md (v4) - Token optimization

beast-mode.md (separate lineage) - Research-focused workflow
```

---

## 🔄 Version History

- **v1 (Original)**: Comprehensive baseline with all features
- **v3 (Condensed)**: Length reduction while preserving core functionality
- **v4 (Compact)**: Token optimization for lower-reasoning LLMs (-70% tokens)
- **v5 (Auto)**: Autonomous execution optimization + context drift prevention
- **v5.1 (All)**: Event-driven context management (phase-based, not turn-based)
- **v5.2 (Auto, Condensed, Compact)**: Memory management system added; removed duplicate context sections
- **Beast Mode**: Separate research-focused workflow with URL fetching + reactive memory

---

## 📝 Notes

- All versions except Beast Mode share the same core Claudette identity
- Token estimates based on ~1.33 tokens per word average
- **NEW**: All Claudette versions now include event-driven context drift prevention
- Context drift triggers: phase completion, state transitions, uncertainty, pauses
- Beast Mode has a distinct philosophy focused on research and URL fetching
- All versions emphasize autonomous execution and completion criteria
- Event-driven approach replaces turn-based context management (industry best practice)