Kalshi Economic Nowcast Trader#

This is a template.

The default signal uses the Cleveland Fed CPI Nowcast point estimate and standard deviation to price CPI bins -- remix it with real-time nowcast scraping, multiple nowcast sources, or Bayesian updating as data arrives.

The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.

Strategy Overview#

Kalshi lists CPI bin markets ("Will CPI be between 0.2% and 0.3%?"). This skill prices each bin using the Cleveland Fed's CPI Nowcast as the mean of a normal distribution, then trades when the market price diverges from the model probability.

Key advantages:

• Cleveland Fed Nowcast is free and public -- updated regularly with high accuracy
• Normal distribution is well-calibrated for CPI -- historically fits actual outcomes
• Multiple bins per release -- diversified signal across the distribution

Signal Logic#

Nowcast-to-Bin Model#

1. Load Cleveland Fed CPI Nowcast estimate and standard deviation
2. Compute P(CPI in [low, high]) = Phi(z_high) - Phi(z_low) for each bin
3. Compare model probability to Kalshi market price
4. Trade when |model - market| >= entry_edge

Example (with defaults: estimate=0.3%, stddev=0.15%)#

BinModel PMarket PEdgeAction0.1%-0.2%9.2%15%-5.8%Hold0.2%-0.3%34.1%20%+14.1%BUY YES0.4%-0.5%9.2%22%-12.8%BUY NO

Remix Ideas#

• Live nowcast scraper: Auto-refresh from Cleveland Fed website
• Multi-source ensemble: Average Cleveland Fed, NY Fed, and Atlanta Fed nowcasts
• Bayesian updates: Incorporate PPI, import prices, and other leading indicators
• Volatility scaling: Widen stddev near data release dates

Risk Parameters#

ParameterDefaultNotesEntry edge10%Min model-vs-market divergence to tradeExit threshold45%Sell when position price reaches thisMax position size$5.00 USDCPer marketMax trades per run3Rate limitingMax slippage15%Skip if slippage exceedsMin liquidity$0Disabled by default

Installation & Setup#

bash

clawhub install kalshi-econ-nowcast-trader

Requires: SIMMER_API_KEY and SOLANA_PRIVATE_KEY environment variables.

Cron Schedule#

Cron is set to null -- the skill does not run on a schedule until you configure it in the Simmer UI.

Safety & Execution Mode#

The skill defaults to dry-run mode. Real trades only execute when --live is passed explicitly.

ScenarioModeFinancial riskpython trader.pyDry runNoneCron / automatonDry runNonepython trader.py --liveLive (Kalshi via DFlow)Real USDC

The automaton cron is set to null -- it does not run on a schedule until you configure it in the Simmer UI. autostart: false means it won't start automatically on install.

Required Credentials#

VariableRequiredNotesSIMMER_API_KEYYesTrading authority. Treat as a high-value credential.SOLANA_PRIVATE_KEYYesBase58-encoded Solana private key for live trading.

Tunables (Risk Parameters)#

All risk parameters are declared in clawhub.json as tunables and adjustable from the Simmer UI without code changes.

VariableDefaultPurposeSIMMER_ECON_NOW_ENTRY_EDGE``0.10Min divergence between nowcast model and market to trigger tradeSIMMER_ECON_NOW_EXIT_THRESHOLD``0.45Sell position when price reaches this levelSIMMER_ECON_NOW_MAX_POSITION_USD``5.00Max USDC per tradeSIMMER_ECON_NOW_MAX_TRADES_PER_RUN``3Max trades per execution cycleSIMMER_ECON_NOW_SLIPPAGE_MAX``0.15Max slippage before skipping (0.15 = 15%)SIMMER_ECON_NOW_MIN_LIQUIDITY``0Min market liquidity USD (0 = disabled)

Dependency#

simmer-sdk is published on PyPI by Simmer Markets.

• PyPI: https://pypi.org/project/simmer-sdk/
• GitHub: https://github.com/SpartanLabsXyz/simmer-sdk
• Publisher: hello@simmer.markets

Review the source before providing live credentials if you require full auditability.