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.
npx skills add DanielTomaro13/sportsdata-agents --skill build_a_h2h_modelgit clone --depth 1 https://github.com/DanielTomaro13/sportsdata-agentsWrote 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.
[](https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/build_a_h2h_model)<a href="https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/build_a_h2h_model"><img src="https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/build_a_h2h_model/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.
<a href="https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/build_a_h2h_model"><img src="https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/build_a_h2h_model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00454 |
| Opus 5 | $0.00019 | $0.00227 |
| Sonnet 5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
build_a_h2h_model 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.
What it actually says
Build a head-to-head (winner) model — worked example
Follow model_development for the method; this is the h2h instantiation.
Recipe (run_python, one script)
- Data: results for the competition, as many seasons as the regime allows (count events: §2 of model_development). Print what you kept and dropped.
- Ratings as the core feature: maintain an Elo-style rating per team —
r_new = r_old + K * (outcome - expected),expected = 1/(1+10^(-(r_a-r_b)/400)). Tune K on the training slice only (typical 16–32). Ratings compress a team's whole history into one number — ideal for small samples. - Logistic regression on top: features = rating difference, home indicator, rest-days difference if available, plus AT MOST one or two user-valued stats (ask — see model_development §3). Fit on train, freeze, predict holdout.
- Draws (football, etc.): model as multinomial (home/draw/away) or fit P(draw) separately as a function of rating closeness — never silently ignore the draw in a 3-way market.
- Calibrate + persist:
calibration_metricson the holdout →save_model(params: K, coefficients, feature list, seasons used) →record_predictionswith honestpredicted_at.
Sanity anchors
- Home advantage exists in every league; if your fitted home coefficient is negative, suspect a data bug before a discovery.
- Compare against the market baseline: vig-removed closing probs. Beating Elo is easy; beating the close is the bar.
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.
- 11d ago First seen · 34 lines · 38 tokens per session scan A 01c209d52f64
build_a_h2h_model is a skill published in the GitHub repository DanielTomaro13/sportsdata-agents (5 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 454 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.
Other skills, from other repositories
biotech-analyst
Activates BiotechAnalyst for biotech and pharmaceutical investment and competitive analysis. Use when you need clinical pipeline stage analysis and probability-of-success estimation, regulatory pathway assessment (FDA, EMA), biotech valuation using risk-adjusted NPV (rNPV), competitive landscape mapping by indication…
dcf-model
Build discounted cash flow valuation workbooks in Excel.
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
polymarket
Query Polymarket: markets, prices, orderbooks, history.
industry-research
An industry-research workflow that maps how an industry works from suppliers to customers, then examines individual companies within it. The value-investing analysis looks at business quality, risks, and price.