DanielTomaro13/sportsdata-agents

Free, open-source agentic sports-data workbench — 32 specialist agents over live odds + stats from 64 providers: value & arbitrage detection, backtesting with CLV, live monitors, racing, fantasy. Can place bets under a policy you set; defaults to paper, stakes nothing. Runs locally, BYO model key.

6Stars on the repository
13Mods indexed here, across every type
4d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

backtest_design

01

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

How to design and read backtests honestly — lookahead/leakage traps, point-in-time discipline, multiple comparisons, CLV vs ROI, sample size.

not rated 6 4d ago A 36 tokens original MIT

book_navigation

02

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

Verified bookmaker entry points (competition/event ids) for cross-book price lookups, starting with AFL.

not rated 6 4d ago A 23 tokens original MIT

build_a_h2h_model

03

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

Worked example of modeldevelopment for match-winner (h2h/moneyline) markets — ratings + logistic regression, home advantage, draw handling.

not rated 6 4d ago A 38 tokens original MIT

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

Worked example of modeldevelopment for totals (over/under) markets — scoring-process baseline, pace adjustment, holdout evaluation.

not rated 6 4d ago A 32 tokens original MIT

compare_odds

06

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

Cross-bookmaker comparison workflow — find the same selection at every book, surface the best price, and flag value.

not rated 6 4d ago A 27 tokens original MIT

dfs_lineup_building

07

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

DFS lineup workflow — site rules first, projections with stated sources, deterministic optimisation via optimizelineup, stacking/ownership as explicit judgment.

not rated 6 4d ago A 33 tokens original MIT

model_development

08

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

The general model-building method for ANY market — framing, sample-size discipline, feature selection (user priors + data-driven), baselines, leakage-safe validation, calibration, persistence.

not rated 6 4d ago A 40 tokens original MIT

prediction_markets

09

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

How to read prediction markets (Kalshi, Polymarket) — price-as-probability, resolution rules before any comparison, fees/spread, and comparing exchange contracts to book odds honestly.

not rated 6 4d ago A 43 tokens original MIT

quant_concepts

10

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

Working definitions of the core quant concepts — Brier, log-loss, calibration, logistic regression, gradient boosting/XGBoost, regularization, walk-forward CV, CLV — and when each tool fits.

not rated 6 4d ago A 45 tokens original MIT

reading_a_racecard

11

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

How to read a racecard honestly — barrier/weight/form/scratchings, converting prices to fair probability (overround/vig), cross-book best price, and exotics.

not rated 6 4d ago A 42 tokens original MIT

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

Interpreting captured line movement — steam vs drift, why the close is the benchmark, and how movement context changes a value report.

not rated 6 4d ago A 32 tokens original MIT

vig_removal

13

DanielTomaro13/sportsdata-agents

Skill Claude CodeCodex

Remove the bookmaker margin (vig/overround) to estimate fair probabilities and spot value.

not rated 6 4d ago A 22 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: