BrainBytesandClaude Opus 4.6
9a8fcfcaac
The complete trading and quantitative finance system for Claude Code. - 18 specialized agents (quant-researcher, algo-strategist, risk-manager, derivatives-analyst, etc.) - 82 domain skills across 10 categories (quant methods, strategies, risk, derivatives, portfolio, execution, data, crypto, macro, backtesting) - 20 slash commands for trading workflows - 5 always-active rules (risk limits, data integrity, model governance, regulatory compliance, ethical trading) - 4 hook scripts (risk check, backtest validation, data quality, session start) - 3 context modes (research, live-trading, backtesting) - 3 example configs (quant fund, crypto trader, retail algo) - 8 MCP server configurations - The Complete Guide (setup + advanced patterns) - Viral-ready README, CONTRIBUTING, CI, PR template Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2.5 KiB
2.5 KiB
Systematic Quant Fund
Multi-strategy systematic fund running daily rebalancing across equity, fixed income, and commodity futures. Risk parity allocation framework with factor-based alpha models.
Architecture
- Strategy layer: 8 alpha models (momentum, value, quality, carry, mean-reversion, event-driven, sentiment, volatility)
- Portfolio layer: Risk parity allocation across strategies, daily rebalancing
- Execution layer: TWAP/VWAP execution with smart order routing
- Risk layer: Real-time risk monitoring with automated circuit breakers
Risk Limits
- Maximum gross leverage: 3.0x
- Maximum single strategy allocation: 25%
- Portfolio-level VaR (99%, 1-day): 1.5% of NAV
- Maximum drawdown trigger: -8% (reduce to 50% exposure)
- Maximum single-name position: 2% of NAV
- Maximum sector concentration: 20%
Data Pipeline
- Market data: Polygon.io real-time + daily OHLCV
- Fundamentals: SEC EDGAR filings, point-in-time
- Alternative data: NLP sentiment from earnings calls, satellite data for commodities
- Update frequency: Daily at 18:00 ET, real-time for risk monitoring
Models
All models follow the governance framework:
- Walk-forward validation with 5 out-of-sample windows minimum
- Deflated Sharpe ratio reported for all strategies
- Monthly model performance monitoring
- Quarterly re-validation against live performance
- Maximum 10 free parameters per model
Rebalancing
- Frequency: Daily at market open
- Method: Target weights from optimizer, constrained by turnover limits
- Turnover budget: 5% of NAV per day maximum
- Transaction cost model: 3bps for large-cap equities, 8bps for small-cap, 2bps for futures
Compliance
- MiFID II best execution documentation for all trades
- Daily position limit checks against exchange limits
- Weekly compliance report generation
- All algorithmic trading registered with regulators
- Kill switch tested monthly
Commands Used Frequently
/risk-report— Daily morning risk report/factor-analysis— Weekly factor exposure review/market-regime— Daily regime classification for strategy weighting/stress-test— Weekly stress test against historical scenarios/trade-review— Monthly performance attribution/correlation-check— Weekly correlation monitoring/alpha-decay— Quarterly signal decay assessment
Agents
Primary agents: quant-researcher, risk-manager, portfolio-manager, execution-specialist
Supporting agents: algo-strategist, backtesting-engineer, financial-data-scientist