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 edushinka/betbetter-mcp --skill betbettergit clone --depth 1 https://github.com/edushinka/betbetter-mcpWrote 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/edushinka/betbetter-mcp/betbetter)<a href="https://agentmods.dev/skills/edushinka/betbetter-mcp/betbetter"><img src="https://agentmods.dev/badge/skills/edushinka/betbetter-mcp/betbetter/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/edushinka/betbetter-mcp/betbetter"><img src="https://agentmods.dev/badge/skills/edushinka/betbetter-mcp/betbetter.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 | $0.00052 | $0.00446 |
| Opus 5.5 | $0.00021 | $0.00178 |
| Sonnet 5.5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
betbetter-sports-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 7d 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
Bet Better sports model
Bet Better publishes a free, read-only feed of its model output. No API key, no sign-up, CORS on, licensed CC BY 4.0. Full reference: Bet Better API docs.
Feeds
Add ?format=json to any feed.
| Feed | Path | Example |
|---|---|---|
| Ranked picks | /{league}/picks |
https://betbetter.world/nba/picks?format=json |
| Player props | /{league}/prop-bets |
https://betbetter.world/nba/prop-bets?format=json |
| Predicted scores | /predicted-scores/{sport} |
https://betbetter.world/predicted-scores/nba?format=json |
| Fantasy projections | /fantasy/{sport} |
https://betbetter.world/fantasy/ |
Some rows are members-only. They show the game, start time and market, with the numbers set to null. Treat null as "not available", not as zero.
Cache for 15 minutes. Do not poll in a tight loop.
Steps
- Work out the league from the request (nba, nfl, mlb, nhl, afl, and so on).
- Fetch the feed for that league with
?format=json. - Filter to the team or player the user asked about.
- Report the selection, game, start time, model chance and fair price.
- Say these are model estimates, not bookmaker prices. The feed has no bookmaker odds.
Other ways in
- MCP:
npx betbetter-mcp, source at edushinka/betbetter-mcp. - Python:
pip install betbetter.
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.
- 7d ago First seen · 39 lines · 52 tokens per session scan A 367f7f88c769
betbetter-sports-model is a skill published in the GitHub repository edushinka/betbetter-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 446 once invoked, about $0.0002 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 2026-11-02.
betbetter-sports-model compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| betbetter-sports-modeledushinka/betbetter-mcp | Skill | 0 | 9d ago | MIT | A | 52 | Claude Code, Codex |
| research-handigraphs-filtersHandigraphs/handigraphs-stats-api-mcp | Skill | 0 | yesterday | Apache-2.0 | A | 64 | Claude Code, Codex |
| query-handigraphs-statsHandigraphs/handigraphs-stats-api-mcp | Skill | 0 | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| setup-handigraphs-stats-apiHandigraphs/handigraphs-stats-api-mcp | Skill | 0 | yesterday | Apache-2.0 | A | 89 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 3d ago | Apache-2.0 | A | 187 | Claude Code |
| dcc-blender-assembly-pitfallsdcc-mcp/dcc-mcp-blender | Skill | 62 | yesterday | MIT | A | 153 | Claude Code |
| virality-analysismtarcure/claude-vibe-squad | Skill | 228 | 12d ago | MIT | A | 56 | Claude Code, Codex |