starknet-defi

starknet-defi is a skill for Claude Code, Codex from keep-starknet-strange/starknet-agentic. It costs 41 tokens per session (2,545 once invoked), scanned A, original, MIT.

A tool guide for carrying out decentralized-finance operations on Starknet, a blockchain network. It covers token swaps, recurring purchases, STRK staking, and lending or borrowing.

In plain words
What is it for?
Use it to get swap quotes and execute swaps, set up recurring buys, stake STRK, lend or borrow tokens, and use transactions where the user does not pay the network fee directly.
Why use it?
It helps code agents perform these financial workflows through Starknet protocols instead of requiring separate instructions for each operation.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present.

Part of the starknet-agentic-skills plugin — 19 skills, 2 commands, 1 plugin shipped together

Good fit Use it to get swap quotes and execute swaps, set up recurring buys, stake STRK, lend or borrow tokens, and use transactions where the user does not pay the network fee directly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/keep-starknet-strange/starknet-agentic/starknet-defi
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 keep-starknet-strange/starknet-agentic --skill starknet-defi
Clone the repo
git clone --depth 1 https://github.com/keep-starknet-strange/starknet-agentic

Made for: Claude Code, Codex.

Or install starknet-agentic-skills, the plugin that ships this one along with the rest of its 19 skills, 2 commands, 1 plugin.

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 starknet-defi

README.md
[![agentmods](https://agentmods.dev/badge/skills/keep-starknet-strange/starknet-agentic/starknet-defi/github.svg)](https://agentmods.dev/skills/keep-starknet-strange/starknet-agentic/starknet-defi)
Your own site
<a href="https://agentmods.dev/skills/keep-starknet-strange/starknet-agentic/starknet-defi"><img src="https://agentmods.dev/badge/skills/keep-starknet-strange/starknet-agentic/starknet-defi/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 starknet-defi

Your own site · 80×15
<a href="https://agentmods.dev/skills/keep-starknet-strange/starknet-agentic/starknet-defi"><img src="https://agentmods.dev/badge/skills/keep-starknet-strange/starknet-agentic/starknet-defi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,545 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 $0.00041 $0.02545
Opus 5 $0.00020 $0.01273
Sonnet 5 $0.00008 $0.00509
Haiku 4.5 $0.00004 $0.00254

Measured 12d ago against content hash 16e6c4a44ae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

starknet-defi 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 12d 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.

skills/starknet-defi/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Starknet DeFi Skill

Execute DeFi operations on Starknet using avnu aggregator and native protocols.

When to Use

  • Swaps, DCA orders, staking, and lending or borrowing flows on Starknet.
  • Agent workflows that need AVNU routing, paymaster support, or protocol-specific DeFi execution.

When NOT to Use

  • Plain wallet management without DeFi intent.
  • Cairo contract authoring, deployment operations, or security auditing.

Quick Start

  1. Install the AVNU + starknet.js dependencies and point the skill at a funded Starknet account.
  2. Use skills catalog when the flow expands into wallet setup, deployment, or auditing.

Prerequisites

npm install starknet@^8.9.1 @avnu/avnu-sdk@^4.0.1

Token Swaps (avnu SDK v4)

Get Quote and Execute Swap

import { getQuotes, executeSwap, type QuoteRequest } from "@avnu/avnu-sdk";
import { Account, RpcProvider, ETransactionVersion } from "starknet";

const provider = new RpcProvider({ nodeUrl: process.env.STARKNET_RPC_URL });

// starknet.js v8: Account uses options object
const account = new Account({
  provider,
  address,
  signer: privateKey,
  transactionVersion: ETransactionVersion.V3,
});

// Resolve token addresses via avnu SDK (or use MCP server's TokenService)
import { fetchVerifiedTokenBySymbol } from '@avnu/avnu-sdk';

const eth = await fetchVerifiedTokenBySymbol('ETH');
const strk = await fetchVerifiedTokenBySymbol('STRK');

// SDK v4: getQuotes takes QuoteRequest object directly
const quoteParams: QuoteRequest = {
  sellTokenAddress: eth.address,
  buyTokenAddress: strk.address,
  sellAmount: BigInt(10 ** 17), // 0.1 ETH
  takerAddress: account.address,
};

const quotes = await getQuotes(quoteParams);
const bestQuote = quotes[0];

// SDK v4: executeSwap takes single object param
const result = await executeSwap({
  provider: account,
  quote: bestQuote,
  slippage: 0.01, // 1%
  executeApprove: true,
});
console.log("Tx:", result.transactionHash);

Quote Response Fields (SDK v4)

Read the full file on GitHub · 341 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. 12d ago First seen · 341 lines · 41 tokens per session scan A 16e6c4a44ae9

Subscribe to this mod's changes

starknet-defi is a skill published in the GitHub repository keep-starknet-strange/starknet-agentic (80 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 2,545 once invoked, about $0.0002 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.