jupiter-lend

jupiter-lend is a skill for Claude Code from jup-ag/agent-skills. It costs 68 tokens per session (6,155 once invoked), scanned A, original, MIT.

A software development kit for reading and changing lending positions on Jupiter Lend, a lending and borrowing service on the Solana blockchain.

In plain words
What is it for?
Use it to query markets and positions, deposit or withdraw funds, manage collateral, borrow, repay, or work with vaults.
Why use it?
It gives code access to liquidity pools, lending markets, vaults, balances, and lending transactions in one integration.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to query markets and positions, deposit or withdraw funds, manage collateral, borrow, repay, or work with vaults.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jup-ag/agent-skills/jupiter-lend
Install

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.

Any agent
npx skills add jup-ag/agent-skills --skill jupiter-lend
Clone the repo
git clone --depth 1 https://github.com/jup-ag/agent-skills

Made for: Claude Code.

Or install claude, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for jupiter-lend

README.md
[![agentmods](https://agentmods.dev/badge/skills/jup-ag/agent-skills/jupiter-lend/github.svg)](https://agentmods.dev/skills/jup-ag/agent-skills/jupiter-lend)
Your own site
<a href="https://agentmods.dev/skills/jup-ag/agent-skills/jupiter-lend"><img src="https://agentmods.dev/badge/skills/jup-ag/agent-skills/jupiter-lend/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.

agentmods 80×15 button for jupiter-lend

Your own site · 80×15
<a href="https://agentmods.dev/skills/jup-ag/agent-skills/jupiter-lend"><img src="https://agentmods.dev/badge/skills/jup-ag/agent-skills/jupiter-lend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.06155
Opus 5 $0.00034 $0.03078
Sonnet 5 $0.00014 $0.01231
Haiku 4.5 $0.00007 $0.00615

Measured 10d ago against content hash 85c0934e2df2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

jupiter-lend 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 10d 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.

.plugins/integrate-jupiter/claude/skills/jupiter-lend/SKILL.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jupiter Lend Protocol

Jupiter Lend (powered by Fluid Protocol) is a lending and borrowing protocol on Solana. It offers Liquidity Pools, Lending Markets (jlTokens), and Vaults for leveraged positions.

The protocol uses two main SDKs:

  • @jup-ag/lend-read: Read-only queries for all programs (Liquidity, Lending, Vaults)
  • @jup-ag/lend: Write operations (deposit, withdraw, borrow, repay)

Agent usage

Example prompts you can use to demo Jupiter Lend integrations:

  • Discover all available vaults and list them
  • Fetch all vault positions for a user
  • Deposit collateral and borrow in a single transaction
  • Repay max debt and withdraw max collateral for a position
  • Get user Earn (jlToken) positions and underlying balances
  • Build a flashloan for arbitrage or liquidation
  • Get liquidity rates and APY for a token
  • Create a new vault position (positionId 0), deposit collateral, and borrow

SDK Installation

# For read operations (queries, prices, positions)
npm install @jup-ag/lend-read

# For write operations (transactions)
npm install @jup-ag/lend

1. Key Concepts & Protocol Jargon

Understanding the architecture and terminology of Jupiter Lend will help you build better integrations.

Architecture: The Two-Layer Model

  • Liquidity Layer (Single Orderbook): The foundational layer where all assets reside. It manages token limits, rate curves, and unified liquidity. Users never interact with this directly.
  • Protocol Layer: User-facing modules (Lending and Vaults) that sit on top of the Liquidity Layer and interact with it via Cross-Program Invocations (CPIs).

Terminology

  • jlToken (Jupiter Lend Token): The yield-bearing asset you receive when supplying tokens to the Lending protocol (e.g., jlUSDC). As interest accrues, the exchange rate increases, making your jlToken worth more underlying USDC.
  • Exchange Price: The conversion rate used to translate between "raw" stored amounts and actual token amounts. It continuously increases as interest is earned on supply or accrued on debt.
  • Collateral Factor (CF): The maximum Loan-to-Value (LTV) ratio allowed when opening or managing a position.
  • Liquidation Threshold (LT): The LTV at which a position becomes undercollateralized and eligible for liquidation.
  • Liquidation Max Limit (LML): The absolute maximum LTV limit. If a position's risk ratio exceeds this boundary, it is automatically absorbed by the protocol to protect liquidity providers.
  • Liquidation Penalty: The discount percentage offered to liquidators when they repay debt on behalf of a risky position.
  • Rebalance: An operation that synchronizes the upper protocol layer's accounting (Vaults/Lending) with its actual position on the Liquidity layer. It also syncs the orderbook to account for any active accrued rewards.
  • Tick-based Architecture: The Vaults protocol groups positions into "ticks" based on their risk level (debt-to-collateral ratio). This allows the protocol to efficiently manage risk and process liquidations at scale.
  • Dust Borrow: A tiny residual amount of debt intentionally kept on positions to handle division rounding complexities.
  • Sentinel Values: Constants like MAX_WITHDRAW_AMOUNT and MAX_REPAY_AMOUNT that tell the protocol to dynamically calculate and withdraw/repay the maximum mathematically possible amount for a position.

Read the full file on GitHub · 597 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 10d ago First seen · 597 lines · 68 tokens per session scan A 85c0934e2df2

Subscribe to this mod's changes

jupiter-lend is a skill published in the GitHub repository jup-ag/agent-skills (83 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 6,155 once invoked, about $0.0003 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.