Add TraderHarness (#489)

Co-authored-by: Wilson Freitas <wilson.freitas@gmail.com>

README.md

@@ -302,6 +302,7 @@ A curated list of insanely awesome libraries, packages and resources for Quants
 - [TradeClaw](https://github.com/naimkatiman/tradeclaw) - `Node.js` `TypeScript` - Open-source self-hosted AI trading signal platform. Generates buy/sell signals using RSI, MACD, EMA, Bollinger Bands for forex, crypto and commodities. Deployable via Docker Compose. ([Demo](https://tradeclaw.win/dashboard))
 - [ShowMe](https://github.com/nazmiefearmutcu/showMe) - `Python` `Rust` `TypeScript` - Open-source native macOS market cockpit. 12-timeframe consensus scan across 3370 symbols (crypto + equity + ETF + FX + commodity + bond), 23 technical indicators with per-market calibration, real WebSocket streaming. Tauri shell + Python sidecar (FastAPI) + React UI; 110+ exchanges via ccxt.
 - [TBV1](https://github.com/nazmiefearmutcu/TRADING-BOT) - `Python` - Crypto perpetual-futures bot with a 7-tab web dashboard and a 15-indicator consensus engine voting across 12 timeframes (1m → 1d). Paper-mode by default. Includes packaged macOS reference build and Windows distribution.
+- [TraderHarness](https://github.com/HephaestLab/TraderHarness) - `Python` - Contamination-resistant A-share backtesting environment for LLM trading agents with point-in-time masking, entity/date anonymization, fingerprinted replay, and trajectory (SFT) export.
 - [VerumTrade](https://github.com/muye1202/VerumTrade) - `Python` - A reasoning & decision-trace visible Multi-agent LLM trading-research framework where bull/bear analysts debate each ticker and every decision cites the evidence it rests on.
 
 ## Portfolio Optimization & Risk Analysis