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.
npx skills add eugenepyvovarov/mcpbundler-agent-skills-marketplace --skill raydiumgit clone --depth 1 https://github.com/eugenepyvovarov/mcpbundler-agent-skills-marketplaceWrote 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/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/raydium)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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 });
What ships with it
11 files 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.
- docs/clmm-guide.md 7.7 KB
- docs/troubleshooting.md 8.0 KB
- examples/clmm-pool/README.md 5.8 KB
- examples/clmm-position/README.md 9.8 KB
- examples/cpmm-pool/README.md 8.7 KB
- examples/liquidity/README.md 7.5 KB
- examples/swap/README.md 7.0 KB
- resources/pool-types.md 5.6 KB
- resources/program-ids.md 5.0 KB
- resources/sdk-api-reference.md 7.1 KB
- templates/raydium-setup.ts 8.3 KB runs code
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.
- 12d ago First seen · 233 lines · 0 tokens per session scan A 34e14585894f
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.
Other skills, from other repositories
clawallex-skill
Pay for anything with USDC — virtual cards for any online checkout.
a16z-crypto
Use when evaluating crypto networks and companies through an a16z crypto lens: web3 adoption, infrastructure vs apps, open networks, and long-duration crypto ecosystem investing.
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
cryptocred-structure
Use when evaluating crypto charts through a CryptoCred-style structure lens: levels, confluence, market structure, risk definition, and educational technical process.
willy-woo-onchain
Use when evaluating Bitcoin and crypto cycles through a Willy Woo-style on-chain lens: holder behavior, realized value, supply dynamics, and on-chain demand.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…