reading_a_racecard

reading_a_racecard is a skill for Claude Code, Codex from DanielTomaro13/sportsdata-agents. It costs 42 tokens per session (535 once invoked), scanned A, original, MIT.

A guide to reading a racecard, the list of runners and relevant facts for a horse race, and judging betting prices. It covers barriers, carried weight, recent results, scratchings, and the bookmaker’s margin.

In plain words
What is it for?
Use it to compare runners, assess recent form and race conditions, calculate fair probabilities from prices, find the best available price, and consider combination bets.
Why use it?
It helps turn race information and quoted prices into more realistic chances, while accounting for changes such as late scratchings and the bookmaker’s built-in margin.

Skill for Claude CodeCodex

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

Good fit Use it to compare runners, assess recent form and race conditions, calculate fair probabilities from prices, find the best available price, and consider combination bets.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/reading_a_racecard"><img src="https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/reading_a_racecard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 535 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 $0.00042 $0.00535
Opus 5 $0.00021 $0.00267
Sonnet 5 $0.00008 $0.00107
Haiku 4.5 $0.00004 $0.00053

Measured 12d ago against content hash e7d9196f81e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reading_a_racecard 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 12d 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/reading_a_racecard/SKILL.md · 41 lines

What it actually says

Reading a racecard

A racecard is the runners for one race with the facts that move prices. Read it in this order, and never quote a price without checking for late scratchings first.

Fields that matter

  • Barrier (gate/box) — inside draws suit some tracks/distances; wide draws cost ground. Note it; don't over-weight it.
  • Weight — handicaps carry weight to level the field; a big weight rise on a proven horse is a negative, a drop a positive.
  • Jockey / driver / trainer — strike-rate context, not destiny. Top stables and hoops shorten prices; that's often already in the market.
  • Form string — recent placings (e.g. 1-3x2): x = a spell, numbers = finish positions, 0 = out of the placings. Recency and class of those runs matter more than the raw numbers.
  • Scratchings — a scratched runner changes every other runner's chance and the market percentage. ALWAYS re-pull the card for scratchings before quoting.

Turning prices into probability

  • Win market: convert each price to an implied probability (1/price), sum them — the total exceeds 1 by the overround (the book's margin). vig_removal normalises the field to fair probabilities; compare fair prob to the price you can actually get.
  • Place markets and each-way pay fractions of the win odds — never compare a win price to a place price as if they're the same market.

Cross-book and exotics

  • The best win price is rarely at the same book across runners — quote the book and the price, per runner (best_price).
  • For multis/SRM, surface the book's same_race_multi suggestions and their combined price; don't hand-roll combinations or imply a guaranteed collect.

Honesty

Racing is high-variance. Report form, fair probability and the best price; the user decides. Never call a horse a "good thing", a "lock", or a "special".

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. 12d ago First seen · 41 lines · 42 tokens per session scan A e7d9196f81e5

Subscribe to this mod's changes

reading_a_racecard is a skill published in the GitHub repository DanielTomaro13/sportsdata-agents (5 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 535 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.