agentmods.dev

phantom-agent-kit CLAUDE.md

Coding instructions for adding Phantom Connect wallets to apps built with React, React Native, or browser JavaScript/TypeScript. They cover wallet connections, transactions, messages, payments, token access, and NFT minting.

In plain words
What is it for?
Use them when building or editing an app that connects to Phantom wallets, signs or sends Solana transactions, manages wallet addresses, or uses Phantom Connect features.
Why use it?
They help avoid unsupported transaction methods, incorrect setup, duplicate browser SDK instances, and unsafe calls when a wallet is not connected.

Instructions file

11 14d ago A scan 680 tokens original MIT
View the source file phantom/phantom-agent-kit
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.

agentmods
npx agentmods add instructions/phantom/phantom-agent-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/phantom/phantom-agent-kit
Per session 680 This file is loaded in full into every session.
When invoked 680 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00680 $0.00680
Opus 5 $0.00340 $0.00340
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 2d ago against content hash b6c80cec7992, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phantom-agent-kit CLAUDE.md 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 2d 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.

CLAUDE.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phantom Connect

Give your agent a wallet. Swap, sign, and manage addresses across Phantom's supported chains — and tap into Phantom's docs for context. This plugin also includes skills, rules, and agents to help scaffold wallet-connected apps with the Phantom Connect SDK across React, React Native, and vanilla JS/TS.

Works with both Cursor and Claude Code.

Skill

Use /phantom-connect to activate the Phantom Connect skill. It covers all three SDKs (React, React Native, Browser), transaction patterns, payments, token-gating, and NFT minting.

SDK Rules

Phantom SDK Best Practices

  • Always use signAndSendTransaction for sending transactions. NEVER use signTransaction — it is NOT supported for embedded wallets.
  • In React apps, wrap the application root in PhantomProvider with a valid config (appId, providers, addressTypes).
  • In vanilla JS/TS apps, initialize a single BrowserSDK instance as a singleton. Never create multiple instances.
  • Wrap connect(), signAndSendTransaction(), signMessage(), and other async SDK calls in try-catch blocks.
  • Check isConnected before signing or transaction operations.
  • Import AddressType from @phantom/browser-sdk only.
  • Register your app in Phantom Portal and use a real appId.

Solana Transaction Safety

  • Always use LAMPORTS_PER_SOL from @solana/web3.js for SOL-to-lamport conversion. Never hardcode 1000000000.
  • For time-sensitive transactions, add priority fees with ComputeBudgetProgram.setComputeUnitPrice().
  • Verify transaction status after sending with connection.getSignatureStatus() or connection.confirmTransaction().
  • Use devnet (https://api.devnet.solana.com) for testing, mainnet-beta (https://api.mainnet-beta.solana.com) for production.
  • Never expose private keys in code. Never ask users to input seed phrases or private keys.

Embedded Wallet Constraints

  • signTransaction and signAllTransactions are NOT supported for embedded wallets. Always use signAndSendTransaction.
  • Default spending limit: $1,000 USD per day per app per user.
  • Social login sessions persist 7 days from the last auth event. Handle session expiration gracefully.
  • Social login (Google, Apple) requires a valid appId from Phantom Portal.
  • React Native apps MUST import react-native-get-random-values as the very first import, before anything else.

Read the full file on GitHub · 45 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. 2d ago First seen · 45 lines · 680 tokens per session scan A b6c80cec7992

Subscribe to this mod's changes

phantom-agent-kit CLAUDE.md is an instructions file published in the GitHub repository phantom/phantom-agent-kit (11 stars, last pushed 14d ago), licensed MIT. It adds 680 tokens to every session, about $0.0034 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.

Browser automationFrontendMobile
Related

Other instructions, from other repositories

vibetunnel CLAUDE.md

Instructions for amantus-ai/vibetunnel, covering claude.md, project overview, common development commands, building the project and first, ensure poltergeist is running in the project root.

amantus-ai/vibetunnel · 3,458 tokens

serve-sim AGENTS.md

Instructions for EvanBacon/serve-sim, covering native build notes, e2e testing with agent-browser and e2e testing via the serve-sim cli.

EvanBacon/serve-sim · 919 tokens

vibetunnel AGENTS.md

Instructions for amantus-ai/vibetunnel, a project described as: Turn any browser into your terminal & command your agents on the go.

amantus-ai/vibetunnel · 44 tokens

BossConsole AGENTS.md

Instructions for risa-labs-inc/BossConsole, covering agents.md, project overview, essential commands, workflow rules and running commands in a visible terminal pane.

risa-labs-inc/BossConsole · 14,325 tokens

metamask-mobile CLAUDE.md

Claude Code instructions for MetaMask/metamask-mobile, a project described as: Mobile web browser providing access to websites that use the Ethereum blockchain.

MetaMask/metamask-mobile · 5 tokens

full-page-pdf-snap AGENTS.md

Instructions for Bubu89/full-page-pdf-snap, covering agents.md, worum es geht, wo du stehst, vor der ersten änderung and die regeln, die hier anders sind als üblich.

Bubu89/full-page-pdf-snap · 3,543 tokens