raydium

raydium is a skill for Claude Code, Codex from eugenepyvovarov/mcpbundler-agent-skills-marketplace. It costs 0 tokens per session (1,757 once invoked), scanned A, original, MIT.

A development guide for Raydium, a trading and liquidity system on the Solana blockchain. It covers Raydium's automated market makers, which use programmed rules to let people trade tokens and provide liquidity, plus farms and staking rewards.

In plain words
What is it for?
Use it to build applications involving Raydium token swaps, liquidity pools, concentrated or constant-product markets, farms, or staking on Solana.
Why use it?
Building on a blockchain trading system requires choosing the right market model and connecting wallets, tokens, accounts, and the Solana network. The guide collects the relevant Raydium SDK setup and integration patterns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build applications involving Raydium token swaps, liquidity pools, concentrated or constant-product markets, farms, or staking on Solana.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium
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 eugenepyvovarov/mcpbundler-agent-skills-marketplace --skill raydium
Clone the repo
git clone --depth 1 https://github.com/eugenepyvovarov/mcpbundler-agent-skills-marketplace

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin raydium/plugin install raydium after adding the marketplace above.

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 raydium

README.md
[![agentmods](https://agentmods.dev/badge/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium/github.svg)](https://agentmods.dev/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium)
Your own site
<a href="https://agentmods.dev/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium"><img src="https://agentmods.dev/badge/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium/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 raydium

Your own site · 80×15
<a href="https://agentmods.dev/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium"><img src="https://agentmods.dev/badge/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,757 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.
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 $0.00000 $0.01757
Opus 5 $0.00000 $0.00879
Sonnet 5 $0.00000 $0.00351
Haiku 4.5 $0.00000 $0.00176

Measured 12d ago against content hash 34e14585894f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

raydium 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.

The scan reads SKILL.md. This mod also ships 1 executable file (templates/raydium-setup.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

raydium/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Raydium Protocol Integration Guide

A comprehensive guide for building applications with Raydium - Solana's leading AMM and liquidity protocol.

Overview

Raydium is a suite of automated market makers (AMMs) on Solana offering:

  • CLMM - Concentrated Liquidity Market Maker for capital-efficient LP positions
  • CPMM - Constant Product Market Maker with Token22 support (no OpenBook required)
  • AMM - Classic AMM integrated with OpenBook CLOB
  • Farms - Yield farming and staking rewards

Quick Start

Installation

npm install @raydium-io/raydium-sdk-v2
# or
yarn add @raydium-io/raydium-sdk-v2

Basic Setup

import { Raydium } from '@raydium-io/raydium-sdk-v2';
import { Connection, Keypair } from '@solana/web3.js';
import bs58 from 'bs58';

// Setup connection and wallet
const connection = new Connection('https://api.mainnet-beta.solana.com');
const owner = Keypair.fromSecretKey(bs58.decode('YOUR_SECRET_KEY'));

// Initialize SDK
const raydium = await Raydium.load({
  connection,
  owner,
  cluster: 'mainnet',
  disableLoadToken: false, // Load token list
});

// Access token data
const tokenList = raydium.token.tokenList;
const tokenMap = raydium.token.tokenMap;

// Access account data
const tokenAccounts = raydium.account.tokenAccounts;

Pool Types

CLMM (Concentrated Liquidity)

Allows LPs to concentrate liquidity in specific price ranges for higher capital efficiency.

// Fetch CLMM pool
const poolId = 'POOL_ID_HERE';
const poolInfo = await raydium.clmm.getPoolInfoFromRpc(poolId);

// Or from API (mainnet only)
const poolData = await raydium.api.fetchPoolById({ ids: poolId });

CPMM (Constant Product)

Simplified AMM without OpenBook market requirement, supports Token22.

// Fetch CPMM pool
const cpmmPool = await raydium.cpmm.getPoolInfoFromRpc(poolId);

AMM (Legacy)

Classic AMM integrated with OpenBook central limit order book.

// Fetch AMM pool
const ammPool = await raydium.liquidity.getPoolInfoFromRpc({ poolId });

Read the full file on GitHub · 233 lines

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 · 233 lines · 0 tokens per session scan A 34e14585894f

Subscribe to this mod's changes

raydium is a skill published in the GitHub repository eugenepyvovarov/mcpbundler-agent-skills-marketplace (12 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,757 tokens. 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.