Food & Agriculture Trader

> This is a template.

> The default signal is keyword-based market discovery combined with conviction-based sizing and harvest_cycle_bias() — remix it with the data sources listed below.

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

Strategy Overview

Agricultural markets are driven by hard data (USDA reports, satellite crop monitoring) but traded by retail participants who follow headlines. This skill exploits two structural edges without any external API:

1. WASDE & crop calendar timing — Information asymmetry between professional futures traders and Polymarket retail peaks around USDA WASDE release months and planting windows. Trading these windows captures the pro vs retail pricing gap before it closes.
2. Commodity type confidence — Cocoa and coffee (geographically concentrated supply) are dramatically more front-runnable than drought headlines (already crowded) or famine narratives (too complex to time).

Signal Logic

Default Signal: Conviction-Based Sizing with Harvest Cycle Bias

1. Discover active food and agriculture markets on Polymarket
2. Compute base conviction from distance to threshold (0% at boundary → 100% at p=0/p=1)
3. Apply harvest_cycle_bias() — combines WASDE calendar timing with commodity type confidence
4. Size = max(MIN_TRADE, conviction × bias × MAX_POSITION) — capped at MAX_POSITION
5. Skip markets with spread > MAX_SPREAD or fewer than MIN_DAYS to resolution

Harvest Cycle Bias (built-in, no API required)

Two compounding structural edges:

Factor 1 — Crop Calendar / WASDE Timing

Agricultural markets have their highest information asymmetry at two points: (a) during the Northern hemisphere planting window (Mar–May) when yield uncertainty peaks, and (b) around USDA WASDE high-impact release months when professional traders have better reads than retail.

Factor 2 — Commodity Type Confidence

Combined and capped at 1.40x. A cocoa market in August (WASDE month) → 1.20 × 1.25 = 1.40x cap — maximum conviction. A drought headline in October (off-season) → 0.90 × 0.85 = 0.77x — trade very small.

Keywords Monitored

wheat, corn, soybean, coffee, cocoa, sugar, food price, crop yield,
drought, harvest, USDA, FAO, food inflation, famine, supply shock,
alternative protein, Beyond Meat, Impossible Foods, lab-grown,
vertical farming, fertilizer, potash, nitrogen, El Niño crop,
La Niña harvest, WASDE, commodity, rice, palm oil, livestock,
cattle, food security, grain, oilseed

Remix Signal Ideas

• USDA NASS crop progress: Free weekly API during growing season — monitor crop condition ratings as leading indicator before WASDE reflects them
• FAO Food Price Index: Monthly release — trade divergence between FAO trajectory and Polymarket food inflation question pricing
• CME agricultural futures: Replace market.current_probability with CME futures-implied probability to trade the pro vs retail gap directly
• NOAA ENSO forecasts: 3–6 month lead time on El Niño/La Niña impacts on major crop-growing regions — markets rarely incorporate this correctly

Safety & Execution Mode

The skill defaults to paper trading (venue="sim"). Real trades only with --live flag.

autostart: false and cron: null — nothing runs automatically until you configure it in Simmer UI.

Required Credentials

Tunables (Risk Parameters)

All declared as tunables in clawhub.json and adjustable from the Simmer UI.

Dependency

simmer-sdk by Simmer Markets (SpartanLabsXyz)

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