prediction_markets

prediction_markets is a skill for Claude Code, Codex from DanielTomaro13/sportsdata-agents. It costs 43 tokens per session (472 once invoked), scanned A, original, MIT.

A guide to prediction markets such as Kalshi and Polymarket, where contracts pay based on whether an event happens. It explains how prices represent probabilities and how to compare contracts fairly with bookmaker odds.

In plain words
What is it for?
Use it to inspect contract rules, convert prices into implied probabilities, account for spreads and fees, and compare equivalent exchange contracts with sports-book prices.
Why use it?
It prevents misleading comparisons caused by different settlement rules, fees, spreads, or event definitions. It also helps distinguish a genuine pricing difference from a market mismatch.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect contract rules, convert prices into implied probabilities, account for spreads and fees, and compare equivalent exchange contracts with sports-book prices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danieltomaro13/sportsdata-agents/prediction_markets
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add DanielTomaro13/sportsdata-agents --skill prediction_markets
Clone the repo
git clone --depth 1 https://github.com/DanielTomaro13/sportsdata-agents

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prediction_markets

README.md
[![agentmods](https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/prediction_markets/github.svg)](https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/prediction_markets)
Your own site
<a href="https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/prediction_markets"><img src="https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/prediction_markets/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prediction_markets

Your own site · 80×15
<a href="https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/prediction_markets"><img src="https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/prediction_markets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00472
Opus 5 $0.00022 $0.00236
Sonnet 5 $0.00009 $0.00094
Haiku 4.5 $0.00004 $0.00047

Measured 11d ago against content hash 588af2398fc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prediction_markets scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/sportsdata_agents/skills/prediction_markets/SKILL.md · 37 lines

What it actually says

Prediction markets

Prediction markets (Kalshi, Polymarket) trade binary/event contracts that pay 1 unit if an outcome happens and 0 if it doesn't. The contract's price therefore is the market's probability: a contract trading at 0.62 means a 62% implied chance.

Read the resolution rules first

The single biggest mistake is comparing two markets that resolve differently. Before any comparison, read market_detail for the exact question, the settlement source, and the expiry. "Team X wins the title" and "Team X wins the final" are different contracts. If the book's market and the prediction market don't resolve on the same condition, say so and stop — the comparison is invalid.

Price → probability

  • Best bid / best ask (market_prices) bracket the fair value; use the mid for a point estimate and note the spread (wide spread = thin/uncertain market).
  • Do not vig-remove a single binary contract price — it's already a probability. The exchange takes a fee on settlement, not a two-sided overround like a book.

The exchange-vs-book edge

This is the high-value play and why this agent exists:

  1. Take the contract's implied probability (prediction market).
  2. Take the SAME outcome at the sportsbooks (find_fixturebest_prices), and vig_removal the book market to a fair probability.
  3. Compare. A meaningful gap means one side is mispriced relative to the other — report which side is the value, the size of the gap, and the venues. Liquidity and the fee/withdrawal frictions on each venue determine whether it's actually takeable.

Honesty

Surface the probabilities, the gap, and the caveats (thin liquidity, resolution-rule mismatch, fees). The user decides and acts; this agent never trades or bets.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 37 lines · 43 tokens per session scan A 588af2398fc5

Subscribe to this mod's changes

prediction_markets is a skill published in the GitHub repository DanielTomaro13/sportsdata-agents (5 stars, last pushed 8d ago), licensed MIT. It adds 43 tokens to every session and 472 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.