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.
git clone --depth 1 https://github.com/moonpay/skillsWrote 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/plugins/moonpay/skills/moonpay-skills)<a href="https://agentmods.dev/plugins/moonpay/skills/moonpay-skills"><img src="https://agentmods.dev/badge/plugins/moonpay/skills/moonpay-skills/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/plugins/moonpay/skills/moonpay-skills"><img src="https://agentmods.dev/badge/plugins/moonpay/skills/moonpay-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
moonpay-skills 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 1mo 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
{
"name": "moonpay-skills",
"description": "Crypto infrastructure skills for AI agents — wallet management, token trading, cross-chain bridges, fiat on/off ramp, and more via the MoonPay CLI.",
"source": "./",
"strict": false,
"skills": [
"./skills/moonpay-auth",
"./skills/moonpay-block-explorer",
"./skills/moonpay-buy-crypto",
"./skills/moonpay-check-wallet",
"./skills/moonpay-commerce",
"./skills/moonpay-deposit",
"./skills/moonpay-discover-tokens",
"./skills/moonpay-export-data",
"./skills/moonpay-feedback",
"./skills/moonpay-fund-polymarket",
"./skills/moonpay-hardware-wallet",
"./skills/moonpay-mcp",
"./skills/moonpay-missions",
"./skills/moonpay-prediction-market",
"./skills/moonpay-price-alerts",
"./skills/moonpay-scout",
"./skills/moonpay-swap-tokens",
"./skills/moonpay-trading-automation",
"./skills/moonpay-upgrade",
"./skills/moonpay-virtual-account",
"./skills/moonpay-wallet-statusline-refresh",
"./skills/moonpay-wallet-statusline",
"./skills/moonpay-x402"
]
}What it installs
The manifest is a name and a version. 23 skills travel with it, and installing the plugin installs all of them — 818 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill moonpay-scout A 66 tokens
- Skill moonpay-trading-automation A 37 tokens
- Skill moonpay-prediction-market A 37 tokens
- Skill moonpay-block-explorer A 34 tokens
- Skill moonpay-missions A 44 tokens
- Skill moonpay-virtual-account A 50 tokens
- Skill moonpay-commerce A 28 tokens
- Skill moonpay-export-data A 29 tokens
- Skill moonpay-hardware-wallet A 32 tokens
- Skill moonpay-swap-tokens A 33 tokens
- Skill moonpay-deposit A 26 tokens
- Skill moonpay-discover-tokens A 40 tokens
- Skill moonpay-wallet-statusline-refresh A 43 tokens
- Skill moonpay-check-wallet A 33 tokens
- Skill moonpay-feedback A 36 tokens
- Skill moonpay-mcp A 32 tokens
- Skill moonpay-buy-crypto A 26 tokens
- Skill moonpay-x402 A 24 tokens
- Skill moonpay-upgrade A 20 tokens
- Skill moonpay-wallet-statusline B 57 tokens
- Skill moonpay-price-alerts B 29 tokens
- Skill moonpay-auth C 32 tokens
- Skill moonpay-fund-polymarket D 30 tokens
What ships with it
1 file beside marketplace.json#moonpay-skills 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.
- 1mo ago First seen · 31 lines scan A c9a3217ae83b
moonpay-skills is a plugin published in the GitHub repository moonpay/skills (111 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
solana-finance
Develop financial products as Solana Programs in Anchor 1, 2 or Quasar. The companion plugin to the book "Building Financial Software on Solana".
agent-commerce
Put the Agent Commerce Gateway in front of an existing HTTP API so AI agents can call and pay for it with x402.
kamino-lend-plugin
Supply, borrow, and manage positions on Kamino Lend — the leading Solana lending protocol.
aerodrome-amm-plugin
Swap tokens and provide liquidity on Aerodrome AMM (volatile/stable pools) on Base.
pendle-plugin
Pendle Finance yield tokenization plugin — buy/sell PT & YT, add/remove liquidity, mint/redeem PT+YT pairs across Ethereum, Arbitrum, BSC, and Base.
sparklend-plugin
SparkLend lending and borrowing on Ethereum Mainnet — supply, withdraw, borrow, repay, positions, health factor, reserves.