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 aaronjmars/aeon-agent --skill miroshark-matchdaygit clone --depth 1 https://github.com/aaronjmars/aeon-agentWrote 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/aaronjmars/aeon-agent/miroshark-matchday)<a href="https://agentmods.dev/skills/aaronjmars/aeon-agent/miroshark-matchday"><img src="https://agentmods.dev/badge/skills/aaronjmars/aeon-agent/miroshark-matchday/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/aaronjmars/aeon-agent/miroshark-matchday"><img src="https://agentmods.dev/badge/skills/aaronjmars/aeon-agent/miroshark-matchday.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 | $0.00068 | $0.02071 |
| Opus 5.5 | $0.00027 | $0.00828 |
| Sonnet 5.5 | $0.00014 | $0.00414 |
| Haiku 4.5 | $0.00007 | $0.00207 |
Grade A, and why
miroshark-matchday scanned grade A with 1 finding 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 15d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use **WebFetch** for the `/suggest`, `/status`, and `/report` reads if `curl` is blocked — they're public, no auth. Only the `POST /run` payment must go through the Finance District wallet tools. How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
${var} — Empty → the default three leagues (Premier League, Serie A, La Liga) for the upcoming matchday. A comma-separated subset (
pl,seriea) runs fewer sims. Any other text is treated as ONE custom simulation scenario run as-is.
Every Friday, run one paid MiroShark simulation per major league for the weekend's matchday, then turn each simulation into a video. A sim ingests a scenario, spins up ~20–30 agent personas, runs 10 rounds of simulated social debate plus a prediction market, and publishes a shareable report. Each run costs a flat $1.00 USDC via x402 on Base (gasless for the payer — EIP-3009, no ETH needed).
Spend cap: $4 USDC per run of this skill. Three sims = $3; at most one retry of one failed launch = $4. Never exceed it. A launch that failed AFTER payment settled is reported, never re-paid.
Wallet detection
Payment goes through the operator's Finance District agent wallet (see skills/finance-district-mcp/SKILL.md for the full auth story). Tools surface as mcp__finance-district__* — discover them from the server; don't assume a fixed list.
- No
mcp__finance-district__*tool callable → not connected. Notify once pointing the operator at dashboard → MCP → Connect Finance District, logFD_NOT_CONNECTED, and exit. - Tools return 401 / invalid-token → notify the operator to re-connect once, log
FD_AUTH_STALE, and exit. - Balance below $3 USDC → notify with the current balance, log
MIROSHARK_INSUFFICIENT_FUNDS, and exit. No silent partial batches — a smaller run is what${var}is for.
Steps
1. Build one matchday prompt per league
For each league in scope:
- WebSearch the league's upcoming matchday — the fixtures played this weekend. Get the matchday number, 3–5 marquee fixtures, and one live storyline (title race, derby, injury, manager under pressure). Never write fixtures from memory of the season; verify by search every time.
- Write a scenario prompt (4–4000 chars): matchday number, the key fixtures, the storyline, and the voices that should argue about it (ultras, club directors, betting analysts, journalists).
- Pin the market with
prediction_market: ONE binary question about a concrete outcome resolvable at the end of the matchday (e.g. "Will X be ranked above Y at the conclusion of Matchday N?"). A pinned sharp question beats letting the sim invent a vague one. - Optional free sanity check:
POST https://x402.miroshark.xyz/suggestwith the topic shows how MiroShark itself would phrase it. Use it to tighten your prompt, not replace it.
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.
- 15d ago First seen · 105 lines · 68 tokens per session scan A dc6879cbb685
miroshark-matchday is a skill published in the GitHub repository aaronjmars/aeon-agent (12 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 2,071 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other skills, from other repositories
strategy-spec
Generates a backtestable, regime-gated mean-reversion TRADING STRATEGY SPEC for a BSC / PancakeSwap token using CoinMarketCap x402 DEX data — and decides what data is even worth paying for first (honest free-vs-paid routing). Produces rules + parameters + a 180-day backtest with a buy-and-hold benchmark. A strategy…
agentpay-route
Find, judge, and pay for the best paid x402 tool/API for a need, within a budget. Use when the agent needs a capability behind a paid API and must choose a provider: "which x402 service / paid API for X", "find a tool for X under $Y", comparing providers, avoiding overpriced or fake/stub endpoints, or routing agent…
agentpay-session
Cap and receipt an AI agent's spending. Open a budget-capped AgentPay session so paid tool/API calls stay under a hard USDC limit and each produces a verifiable receipt + a running ledger. Use when enforcing a spend cap across calls, tracking what an agent spent, or producing an audit trail for autonomous payments.…
aawp
AAWP (AI Agent Wallet Protocol) — the only crypto wallet protocol built exclusively for AI Agents on EVM-compatible blockchains and Solana. Not for humans. The signer is the AI Agent itself, cryptographically bound at wallet creation. Supports wallet lifecycle management, token transfers, DEX swaps, cross-chain…
darwinia
Evolve trading strategies through genetic algorithms and adversarial combat. Run Darwinian selection on BTC data to discover battle-tested strategies. No API keys, no cloud.
clicks-protocol
Integrate Clicks Protocol settlement routing into AI agent projects on Base. Use when building agents that hold, earn, receive, or transfer USDC, when asked about agent treasury management, x402 payment settlement, idle USDC routing, or agent referral attribution.