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.
/plugin marketplace add jup-ag/agent-skillsnpx agentmods add plugins/jup-ag/agent-skills/claudegit clone --depth 1 https://github.com/jup-ag/agent-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/jup-ag/agent-skills/claude)<a href="https://agentmods.dev/plugins/jup-ag/agent-skills/claude"><img src="https://agentmods.dev/badge/plugins/jup-ag/agent-skills/claude.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
claude 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 3d 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": "integrate-jupiter",
"description": "Jupiter integration and documentation skills for Solana, crypto, and finance workflows",
"version": "1.1.1",
"author": {
"name": "Jupiter",
"url": "https://jup.ag"
},
"homepage": "https://jup.ag",
"repository": "https://github.com/jup-ag/agent-skills",
"license": "MIT",
"keywords": ["solana", "jupiter", "defi", "finance", "crypto", "documentation", "swap", "lend", "borrow", "earn", "perps", "trigger", "dex-aggregator", "verification", "vrfd", "token-verification"]
}
What it installs
The manifest is a name and a version. 4 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 223 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 3d ago First seen · 14 lines scan A c199ffd63617
claude is a plugin published in the GitHub repository jup-ag/agent-skills (83 stars, last pushed 1mo ago), 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 2026-08-30.
Other plugins, from other repositories
agents-crypto-trading
Expert agents for cryptocurrency trading, DeFi strategies, and market analysis.
solana-finance-claude-plugin
Expert Solana development with Claude: production-grade Anchor, Quasar, Rust, and TypeScript patterns with a focus on financial correctness — onchain math, escrows, AMMs, vaults, oracle freshness, and slippage. Made by Quicknode.
mainstream-spot-order
Multi-chain DEX spot trading system with 6-signal ensemble, auto-research strategy optimization, and per-pair backtesting across SOL, ETH, BTC, BNB, AVAX, DOGE.
kamino-liquidity-plugin
Kamino Liquidity KVault earn vaults on Solana. Deposit tokens to earn yield, withdraw shares, and track positions.
aerodrome-amm-plugin
Swap tokens and provide liquidity on Aerodrome AMM (volatile/stable pools) on Base.
compound-v2-plugin
Compound V2 exit tool on Ethereum mainnet - redeem, repay, claim COMP for legacy V2 positions. Use compound-v3-plugin for active supply/borrow.