Wolverine Strategy

WOLVERINE v2.0 — HYPE Alpha Hunter

Scanner enters. DSL exits. The scanner NEVER re-evaluates open positions.

CRITICAL AGENT RULES

RULE 1: Install path is /data/workspace/skills/wolverine-strategy/

RULE 2: THE SCANNER DOES NOT EXIT POSITIONS — DSL-ONLY EXITS

This is the single most important rule. When the scanner output contains "_v2_no_thesis_exit": true and the note says "DSL manages exit. Scanner does NOT re-evaluate," that means DO NOT close, modify, or re-evaluate the open position for any reason. The plugin DSL is the ONLY mechanism that can close positions.

v1.1 lost -22.7% because the scanner kept killing positions via "thesis exit" — 25 of 27 trades were chopped by the scanner before DSL could manage them. On HYPE, which wicks 5-10% ROE routinely, the scanner saw every wick as "thesis invalidation" and cut winners that would have run to +30%.

If you close a position because "the thesis changed" or "SM flipped" or "the 4H trend broke," you are violating this rule and will bleed exactly like v1.1 did.

RULE 3: MAX 1 POSITION at a time

Only one HYPE position at a time. Check clearinghouse before every entry.

RULE 4: Scanner output is AUTHORITATIVE

Leverage, margin, direction — use exactly what the scanner says.

RULE 5: Verify runtime is installed on every session start

Run openclaw senpi runtime list. Runtime must be listed. The position tracker auto-detects position opens/closes on-chain and DSL exit is handled by the plugin runtime.

RULE 6: Never modify parameters

RULE 7: 3-hour cooldown between entries

After any position close (DSL floor, timeout, trailing stop), wait 3 hours before the next entry. This prevents revenge trading after a loss.

What Changed From v1.1

The Thesis

HYPE moves 2-4% routinely. At 7x leverage, that's 14-28% ROE. The edge is:

1. Enter only when SM consensus + price momentum + contribution acceleration all align (score 8+)
2. Let DSL manage the position through HYPE's normal volatility
3. Wide Phase 1 floor (-20% ROE) survives the wicks that killed v1.1 entries
4. Trailing tiers don't engage until +15% ROE — no premature profit locking
5. When HYPE runs, it runs hard. One +30% ROE trade pays for 3 losing trades at -10%

v1.1 proof: Trade #6 hit +29.92% ROE (+$112) when the scanner accidentally let it run. That single trade was worth more than all other 13 winners combined.

Exit Management

DSL exit is handled by the plugin runtime via runtime.yaml. The position_tracker scanner auto-detects position opens/closes on-chain. See runtime.yaml for configuration details.

Monitor positions:

• openclaw senpi dsl positions — list all DSL-tracked positions
• openclaw senpi dsl inspect <ASSET> — full position details

Runtime Setup

Step 1: Set your strategy wallet address in runtime.yaml:

sed -i 's/${WALLET_ADDRESS}/<STRATEGY_WALLET_ADDRESS>/' /data/workspace/skills/wolverine-strategy/runtime.yaml

Replace <STRATEGY_WALLET_ADDRESS> with the actual wallet address.

Step 2: Set telegram chat ID for notifications:

sed -i 's/${TELEGRAM_CHAT_ID}/<CHAT_ID>/' /data/workspace/skills/wolverine-strategy/runtime.yaml

Replace <CHAT_ID> with the actual Telegram chat ID.

Step 3: Install the runtime:

openclaw senpi runtime create --path /data/workspace/skills/wolverine-strategy/runtime.yaml

Step 4: Verify:

openclaw senpi runtime list

Bootstrap Gate

On EVERY session start, check config/bootstrap-complete.json. If missing:

1. Read the senpi-trading-runtime skill: cat /data/workspace/skills/senpi-trading-runtime/SKILL.md — this provides all CLI commands for runtime management and DSL position inspection.
2. Verify Senpi MCP
3. Set wallet in runtime.yaml: sed -i 's/${WALLET_ADDRESS}/ACTUAL_ADDRESS/' /data/workspace/skills/wolverine-strategy/runtime.yaml
4. Set Telegram in runtime.yaml: sed -i 's/${TELEGRAM_CHAT_ID}/CHAT_ID/' /data/workspace/skills/wolverine-strategy/runtime.yaml
5. Install runtime: openclaw senpi runtime create --path /data/workspace/skills/wolverine-strategy/runtime.yaml
6. Verify runtime installed: openclaw senpi runtime list
7. Remove old DSL cron (if upgrading): run openclaw crons list, delete any cron containing dsl-v5.py via openclaw crons delete <id>
8. Create scanner cron (3 min, main)
9. Write config/bootstrap-complete.json
10. Send: "WOLVERINE v2.0 online. HYPE hunter. Entry-only scanner. Plugin DSL manages all exits. Waiting for score 8+ setup."

If bootstrap exists, still verify runtime and scanner cron on every session start.

Notification Policy

ONLY alert: Position OPENED (direction, score, reasons, leverage), Position CLOSED BY DSL (P&L, close reason, duration), critical error.

NEVER alert: Scanner found no signal, scanner sees open position and is not re-evaluating, any reasoning about whether to exit an open position.

Expected Behavior

Long periods of silence are expected. HYPE must have SM consensus, 4H/1H alignment, contribution acceleration, AND score 8+ to enter. That's rare. The patience IS the edge.

Files

License

MIT — Built by Senpi (https://senpi.ai).