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 signal-to-trade-demogit 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/signal-to-trade-demo)<a href="https://agentmods.dev/skills/blockrunai/blockrun-mcp/signal-to-trade-demo"><img src="https://agentmods.dev/badge/skills/blockrunai/blockrun-mcp/signal-to-trade-demo/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/signal-to-trade-demo"><img src="https://agentmods.dev/badge/skills/blockrunai/blockrun-mcp/signal-to-trade-demo.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 Excessive Agency · line 25 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00088 | $0.01688 |
| Opus 5 | $0.00044 | $0.00844 |
| Sonnet 5 | $0.00018 | $0.00338 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
signal-to-trade-demo 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 13d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Signal-to-Trade Demo
Run one reproducible chain: discover → verify → analyze → preview → inspect. Treat signals as evidence, never as a promise of profit. Never expose a wallet, credential, order ID, or transaction hash in presentation output.
Read references/demo-cases.md when selecting a case or preparing a fallback.
Hard safety contract
- In a presentation dry-run, do not call wallet, setup, positions, orders, or resources. Those responses can contain wallet-derived identifiers before the final answer is redacted. The presenter performs account readiness privately before screen sharing.
- If the current egress is blocked, never call a funds-affecting action with
confirm:true. Continue with live data and a dry-run order preview only. A Stanford/US presentation is always dry-run mode. - Always preview through
blockrun_polymarket_readaction:"preview". It has no confirmation input and cannot sign or submit an order. A real order requires the user's explicit approval of the exact market, outcome, amount, price/type, and current region eligibility. - Choose the smallest whole-dollar preview from $1–$5 that satisfies the live
min_order_sizeand book depth. Never present a smaller, non-executable preview as valid. Do not split orders to bypass caps. - Paid market-data calls may run in parallel on Base. On Solana keep
@blockrun/llm>= 3.8.4, which is what makes concurrent payments distinct.
1. Private operator preflight
- Confirm the Trading profile exposes nine tools and no image/video/media tool: wallet, price, dex, markets, surf, defi, rpc, polymarket_read, polymarket.
- Before screen sharing, the human operator may check
blockrun_wallet, run setup, and inspect positions/orders. Never include those raw calls in the presentation conversation. - For the live dry-run conversation, begin directly with public market discovery. No account state is required to preview a CLOB order.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 167 lines · 88 tokens per session scan A 958d0567d9a0
signal-to-trade-demo is a skill published in the GitHub repository BlockRunAI/blockrun-mcp (395 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,688 once invoked, about $0.0004 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
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…
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…
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…