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 jbdrak/propprofessor-mcp --skill hermesgit clone --depth 1 https://github.com/jbdrak/propprofessor-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/jbdrak/propprofessor-mcp/hermes)<a href="https://agentmods.dev/skills/jbdrak/propprofessor-mcp/hermes"><img src="https://agentmods.dev/badge/skills/jbdrak/propprofessor-mcp/hermes/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/jbdrak/propprofessor-mcp/hermes"><img src="https://agentmods.dev/badge/skills/jbdrak/propprofessor-mcp/hermes.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 | $0.05025 |
| Opus 5 | $0.00026 | $0.02513 |
| Sonnet 5 | $0.00010 | $0.01005 |
| Haiku 4.5 | $0.00005 | $0.00502 |
Grade A, and why
propprofessor-mcp 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PropProfessor MCP — Agent Skill
What It Does
PropProfessor is an odds analysis engine for AI agents. It screens 36+ sportsbooks, ranks plays by sharp-book consensus and multi-window line movement, enriches candidates with player-context research (news + tweets), and outputs tiered recommendations with Kelly-based staking. Supported leagues: NBA, MLB, NHL, WNBA, Tennis, UFC, Soccer, NCAAB, NCAAF, NFL.
Mandatory Operating Rules
- PropProfessor is manual-only. Call tools only on demand; never create cron jobs, scheduled workflows, polling loops, watchdogs, or background live scans. Public-only settlement or schedule refresh must not call PropProfessor.
- Fail closed on incomplete evidence. Do not recommend rows that are unvalidated, skipped, unresolved, or history-degraded. Treat
lookupStatus: "lookup_failed",validatedUnverified: true,status: "unresolved",incomplete: true,movementDisposition: "unavailable", and missing line-history evidence as stale/unverified—not as a negative signal and not as a bet. - Use standard main lines. Alternate spreads/totals and expanded Game Handicap lines are non-actionable; honor
altLineFilteredand TIER 4/PASS. The requested execution book needs a playable price, not necessarily the best price. - For NCAAF NoVig scans, use the local
todaywindow and scan Moneyline, Point Spread, and Total Points. The CLI uses bounded per-market recovery (80 rows per market, 700-row shortlist ceiling) to keep all-market scans inside the request deadline. A broad scan can still summarize unhydrated alternate rows; only exact rows withmatchedRows: 1,isLive: false, a current NoVig quote, and usable movement history are actionable. - During quick-screen validation, keep the named execution book first in
books; comparison books can follow it for consensus context but must not become the requested execution identity. - Preserve frontend Tennis tournament scope with exact
leagueNamewhen supplied. For Soccer, named frontend competitions such as EPL, La Liga, Serie A, Bundesliga, and Ligue 1 areleagueNamefilters over backend leagueSoccer; pass the generic backend league plus the exact competition scope. Tennis defaults are Moneyline / Total Games / Set Handicap; Game Handicap is explicit-only. - For repository changes, run focused deterministic tests,
npm run install:verify,npm run lint,npm run check:types, and relevant checker/format checks. Keep changes task-scoped, never run live PropProfessor requests as tests, and use a conventional commit with the required co-author trailer only after verification.
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.
- today Changed · +2 lines bb8e4872e99b
- 3d ago First seen · 234 lines · 52 tokens per session scan A 65322c7ac063
propprofessor-mcp is a skill published in the GitHub repository jbdrak/propprofessor-mcp (2 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 5,025 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
stock-api
Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets. Use when the user asks for a stock price, a quote, market data, candlestick/K-line data, or to look up a stock code by company name.
okx-cex-portfolio
This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
recurrent-payment
A recurring-payment workflow for T-Kassa, a payment service. It links a customer's card during an initial payment and later charges that saved payment authorisation for a subscription.
refund-payment
A payment procedure for refunding a completed T-Kassa payment or cancelling a payment that is still on hold. T-Kassa is a payment service, and the procedure can also send the required closing receipt.
rpgmaker-mv-mcp
Use when building, editing or reasoning about an RPG Maker MV game through the RpgMakerMVUltimate MCP server (tools prefixed rpgmaker / the 13 consolidated tools: querydatabase, createdatabaseentry, generatemap, managemapevent, analyzeproject, etc.). Covers the correct workflow so maps, NPCs, chests, shops, doors…