Integration guidance for building browser and mobile Solana applications with Phantom Connect and Helius. Phantom is a crypto wallet that lets users connect and approve blockchain transactions.

Use it for React, React Native, or browser apps involving wallet connections, transaction signing, token access rules, NFT minting, crypto payments, asset data, transaction details, and live updates.

It lays out how to connect wallets and handle blockchain actions while keeping API keys and frontend architecture secure.

phantom — Skill for Cursor by helius-labs/core-ai

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 helius-labs/core-ai --skill phantom

Clone the repo

git clone --depth 1 https://github.com/helius-labs/core-ai

Made for: Cursor.

Or install helius, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/helius-labs/core-ai/phantom/github.svg)](https://agentmods.dev/skills/helius-labs/core-ai/phantom)

Your own site

<a href="https://agentmods.dev/skills/helius-labs/core-ai/phantom"><img src="https://agentmods.dev/badge/skills/helius-labs/core-ai/phantom/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/helius-labs/core-ai/phantom"><img src="https://agentmods.dev/badge/skills/helius-labs/core-ai/phantom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,521 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin 97% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.04521
Opus 5.5	$0.00024	$0.01808
Sonnet 5.5	$0.00012	$0.00904
Haiku 4.5	$0.00006	$0.00452

Measured 3d ago against content hash 5a9218793fcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

phantom scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If they are NOT available, **STOP**. Do NOT attempt to call Helius APIs via curl or any other workaround. Tell the user:

Origin

This is a copy

97% identical to helius-phantom — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

helius-cursor/skills/phantom/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Helius x Phantom — Build Frontend Solana Apps

Helius MCP now uses 10 public tools total, including expandResult. When this skill references a Helius action name like getBalance, parseTransactions, or accountSubscribe, call the matching public tool with action: "<action name>".

You are an expert Solana frontend developer building browser-based and mobile applications with Phantom Connect SDK and Helius infrastructure. Phantom is the most popular Solana wallet, providing wallet connection via @phantom/react-sdk (React), @phantom/react-native-sdk (React Native), and @phantom/browser-sdk (vanilla JS). Helius provides transaction submission (Sender), priority fee optimization, asset queries (DAS), real-time on-chain streaming (WebSockets), wallet intelligence (Wallet API), and human-readable transaction parsing (Enhanced Transactions).

Prerequisites

Before doing anything, verify these:

1. Helius MCP Server

The Helius MCP server should start automatically with this plugin. Check that Helius MCP public tools are available (e.g., heliusWallet, heliusAsset, heliusChain).

If they are NOT available, STOP. Do NOT attempt to call Helius APIs via curl or any other workaround. Tell the user:

The Helius MCP server isn't running. Try restarting Cursor.
If the problem persists, add it manually via Settings > Cursor Settings > MCP
with command: npx [email protected]

2. API Key

Helius: If any Helius MCP tool returns an "API key not configured" error, read references/helius-onboarding.md for setup paths (existing key, agentic signup, or CLI).

3. Phantom Portal

For OAuth login (Google/Apple) and deeplink support, users need a Phantom Portal account at phantom.com/portal. This is where they get their App ID and allowlist redirect URLs. Extension-only flows ("injected" provider) do not require Portal setup.

(No Phantom MCP server or API key is needed — Phantom is a browser/mobile wallet that the user interacts with directly.)

Read the full file on GitHub · 344 lines

Files

What ships with it

16 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.

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.

3d ago Changed 5a9218793fcc
4d ago Changed b6d9fc5f285a
5d ago Changed 7cea8ae2c078
9d ago Changed ce81e6442ac1
1mo ago Changed 5359795b7240
1mo ago First seen · 344 lines · 59 tokens per session scan A b3d2a24f6f0b

Subscribe to this mod's changes

phantom is a skill published in the GitHub repository helius-labs/core-ai (29 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 4,521 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 97% identical to helius-phantom, differing in 38 lines, and is treated as a copy.

Web3 and blockchain ai-tools claude-skills cursor mcp solana

web3-protocol-gtm

Go-to-market strategy for web3 builders - protocols, products, services, and solo founders. Use when planning growth for a crypto protocol, building developer community, crafting CT narrative, planning ecosystem partnerships, preparing grant applications, launching tokens, pricing crypto-native products, or growing as…

tenequm/skills · 70 tokens

privy-integration

Integrates Privy authentication, embedded wallets, and agent payment protocols into web and agentic apps. Covers React SDK (PrivyProvider, hooks, wagmi), Node.js SDK, smart wallets (ERC-4337), x402 and MPP machine payments, Tempo chain, and agentic wallets with policies. Use when setting up Privy auth, creating…

tenequm/skills · 110 tokens

phantom