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 compare_oddsgit 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/compare_odds)<a href="https://agentmods.dev/skills/danieltomaro13/sportsdata-agents/compare_odds"><img src="https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/compare_odds/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/compare_odds"><img src="https://agentmods.dev/badge/skills/danieltomaro13/sportsdata-agents/compare_odds.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 | $0.00027 | $0.00406 |
| Opus 5.5 | $0.00011 | $0.00162 |
| Sonnet 5.5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
compare_odds 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 2mo 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
Comparing odds across bookmakers
The data plane carries many books behind the same capability tags — use that to line up one selection across all of them.
Procedure
- Identify the event once. Resolve the fixture (teams/race, start time) before touching prices, so every book's market is matched to the same event.
- Collect prices per book. Use your market/price tools for each available book. Record, for every quote: book, selection name as that book spells it, decimal odds, and the fetch time. Skip a book rather than guess if its market is missing.
- Best price: call
best_priceover the collected quotes. - Value check (when asked, or when a sharp book is present):
- Take the full market at the sharpest book available and call
vig_removalfor a fair probability. - Call
expected_valuewith that fair probability against the best offered odds. - Only describe a price as "value" when expected_value > 0; show the number.
- Take the full market at the sharpest book available and call
- Report: a compact table of book → odds (with fetch times), the best price, the fair probability and its source book, and EV if computed. Cite which tools/providers every figure came from.
Rules
- Same selection, same market type, same line — never compare a -10.5 spread at one book with -11 at another as if equal.
- Prices move: include fetch times; never present a price as current without one.
- Advisory only: you report and compare — you cannot and do not place anything.
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.
- 2mo ago First seen · 32 lines · 27 tokens per session scan A ab25673ba96f
compare_odds is a skill published in the GitHub repository DanielTomaro13/sportsdata-agents (9 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 406 once invoked, about $0.0001 per session on Opus 5.5. 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.
compare_odds compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compare_oddsDanielTomaro13/sportsdata-agents | Skill | 9 | 5d ago | MIT | A | 27 | Claude Code, Codex |
| x402browser-use/browser-use | Skill | 120k | yesterday | MIT | A | 175 | Claude Code |
| project-graveyardShubhamsaboo/awesome-llm-apps | Skill | 144k | yesterday | Apache-2.0 | A | 127 | Claude Code, Codex |
| vnpy-exportHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 40 | Claude Code, Codex |
| yfinanceHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 41 | Claude Code, Codex |
| connect-recommendstripe/ai | Skill | 2.0k | yesterday | MIT | A | 151 | Claude Code, Codex |
| xlsxMODSetter/SurfSense | Skill | 17k | yesterday | Apache-2.0 | A | 16 | Claude Code, Codex |