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 BlockRunAI/blockrun-mcp --skill prediction-marketsgit clone --depth 1 https://github.com/BlockRunAI/blockrun-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/blockrunai/blockrun-mcp/prediction-markets)<a href="https://agentmods.dev/skills/blockrunai/blockrun-mcp/prediction-markets"><img src="https://agentmods.dev/badge/skills/blockrunai/blockrun-mcp/prediction-markets/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/blockrunai/blockrun-mcp/prediction-markets"><img src="https://agentmods.dev/badge/skills/blockrunai/blockrun-mcp/prediction-markets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 227 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00136 | $0.03755 |
| Opus 5 | $0.00068 | $0.01878 |
| Sonnet 5 | $0.00027 | $0.00751 |
| Haiku 4.5 | $0.00014 | $0.00376 |
Grade A, and why
prediction-markets 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prediction Markets (Predexon)
55 endpoints across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, Binance Futures, sports, and the UMA oracle — one x402 gateway, no Predexon account or API key.
What is worth paying for. Current market lists are free from public APIs. These are not, and cannot be backfilled after the fact:
- History — candlesticks, orderbook snapshots, volume charts, open interest, trade history. Built from continuous ingestion; nobody can reconstruct it retroactively.
- Smart money — leaderboards, cohort stats, top holders, which wallets are positioned where, and which markets high-performing wallets just entered.
- Wallet intelligence — profiles, P&L time series, identity metadata, and on-chain clustering (find the other wallets behind one address).
- Cross-venue canonical IDs — one question, matched across five venues. The basis for arbitrage and consensus.
How to Call from MCP
One tool, three params. Method auto-routes: POST when body is set, GET otherwise.
blockrun_markets({ path: "polymarket/events", params: { limit: "10" } })
blockrun_markets({ path: "polymarket/candlesticks/0xCONDITION_ID", params: { interval: "1440" } })
blockrun_markets({ path: "polymarket/wallet/identities", body: {
addresses: ["0xabc...", "0xdef..."]
}})
Paths are relative — no /api/v1/pm/ prefix. Use agent_id to bill a child agent's budget.
Paid calls can run in parallel on Base: each EIP-3009 authorization carries
its own random nonce, so concurrent calls from one wallet cannot collide.
The Solana payload has no nonce field — distinctness comes from the SDK
(@blockrun/llm >= 3.8.4), so keep that floor if you fan out on Solana.
Current parameter contracts that prevent paid 4xx responses:
- Discover with
markets/search(its search term isq), then resolve the selected market withpolymarket/markets/keyset+condition_id. - On
polymarket/markets{,/keyset}the free-text filter issearch, notq. Usestatus:"open"rather than Gamma'sactive/closed, andsortrather thanorder/ascending.end_after/end_beforeare supported (Unix seconds). - Candlestick
intervalis integer minutes (1440, not1h) and is optional — the server has a default. Which intervals a market can serve varies:1440may work where60returns a paid 400. Optionalstart_time/end_timeare Unix seconds. polymarket/orderbooksrequirestoken_id,start_time, andend_time; the times are Unix milliseconds.- Smart-money needs a smart-wallet criterion:
min_trades,min_volume,min_roi,min_realized_pnl,min_total_pnl,min_win_rate, ormin_profit_factor.windowonly scopes the time range and is not sufficient alone (verified: window-only returns a paid 400). Use{ window: "30d", min_trades: "100" }; narrower cohorts are fine. markets/listingsis retired upstream (410 Gone) — the MCP blocks it before payment.
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.
- 9d ago First seen · 294 lines · 136 tokens per session scan A 7d792b3fee72
prediction-markets is a skill published in the GitHub repository BlockRunAI/blockrun-mcp (393 stars, last pushed 2d ago), licensed MIT. It adds 136 tokens to every session and 3,755 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
x402-list
Discover x402 payment services and on-chain-verified facilitator settlement volume via the x402-list directory. Use when a user or agent needs to find an API/service that accepts x402 (HTTP 402 stablecoin) payments, compare services by reliability and price, check service uptime/health, see whether a service has…
x402
HTTP 402 payment protocol for AI agent commerce — three-actor model (Client, Resource Server, Facilitator), ERC-3009 transferWithAuthorization, server middleware (@x402/express), client patterns in TypeScript and Python, facilitator integration, agent-to-agent payments, pricing strategies, and replay protection. Works…
polymarket-tennis
Build observe-only Polymarket and Kalshi tennis market tooling on the polymarket-tennis Python package (MIT) plus the Live Tennis API free tier. Use when asked for a Polymarket tennis bot or market watcher, a Kalshi tennis trading bot, tennis prediction-market data, Gamma API tennis markets, matching a market to a…
market-research
Use for informational market, industry, company, earnings, or public financial research with Axon, not personalized investment advice.
shop
Use when the user wants Axon-backed product research, product comparisons, review synthesis, budget-aware recommendations, or cart preparation without checkout.
onesource-batch-config
Configure OneSource MCP x402 batch-settlement preferences from the session using the 1sbatchconfig tool — autonomy (ask/auto/off), the "many calls" threshold, the channel deposit multiplier, and the default payment mode. Settings persist across restarts with no config-file editing. Use when the user wants to change…