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 agentmods add rules/helius-labs/core-ai/phantom-walletgit clone --depth 1 https://github.com/helius-labs/core-aiWrote 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/rules/helius-labs/core-ai/phantom-wallet)<a href="https://agentmods.dev/rules/helius-labs/core-ai/phantom-wallet"><img src="https://agentmods.dev/badge/rules/helius-labs/core-ai/phantom-wallet.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00379 |
| Opus 5 | $0.00000 | $0.00189 |
| Sonnet 5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
phantom-wallet 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 5d 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.
What it actually says
SDK Selection
- ALWAYS use
@phantom/react-sdkfor React apps — neverwindow.phantom.solanadirectly or@solana/wallet-adapter-react - ALWAYS use
@phantom/browser-sdkfor vanilla JS / Vue / Svelte / non-React frameworks - ALWAYS use
@phantom/react-native-sdkfor React Native / Expo apps window.phantom.solana(the legacy injected provider) requires@solana/web3.jsv1 types and does NOT work with@solana/kit— use Phantom Connect SDK instead
Portal App ID
- Google and Apple OAuth providers require a Phantom Portal App ID from
phantom.com/portal— extension-only ("injected") does not - The exact redirect URL (including protocol and path) must be allowlisted in Phantom Portal settings or OAuth login will fail
React Native
react-native-get-random-valuesMUST be the very first import in the app entry file — if it comes after anything else, the app will crash on startup
Connection Flow
- Use
useModalandopen()to trigger the connection flow — never auto-connect without user action - ALWAYS handle connection errors gracefully — users can reject the prompt at any time
Security
- Never expose Helius API keys in client-side code — always proxy through a backend
- Client-side token gating is bypassable — always verify token ownership server-side with Helius DAS for valuable content
- Never expose mint authority in frontend code — build NFT mint transactions on the server; the client only signs as the payer
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.
- 5d ago First seen · 33 lines · 0 tokens per session scan A 94c4d78a21d9
phantom-wallet is a cursor rule published in the GitHub repository helius-labs/core-ai (26 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 379 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 cursor rules, from other repositories
flow-configuration
Comprehensive guide to Flow project configuration covering flow.json structure, CLI workflow, FCL integration, network management, and deployment best practices. Covers contract aliases, account management, dependency resolution, frontend FCL setup with React SDK, and environment-based configuration for seamless…
cadence-nft-standards
Comprehensive standards and best practices for developing Non-Fungible Tokens (NFTs) using Cadence. Ensures proper implementation of NonFungibleToken interfaces, MetadataViews integration for marketplace compatibility, secure resource handling patterns, and advanced modular architectures for complex NFTs with traits…
flow-development-workflow
Streamlined Flow development workflow covering documentation-first debugging methodology, iterative development approach, deployment verification, gas optimization strategies, and comprehensive testnet validation protocols. Focuses on practical workflows and error prevention rather than configuration details.
user-preferences
Defines personalized development preferences and communication style for Flow blockchain development including concise response formatting, documentation-driven problem solving, iterative workflow methodology, full-stack awareness, and systematic error resolution. Guides AI behavior to match user's preferred…
ai-generation-entrypoint
Start here — Happy Path (Restake): workflows/restaking-workflow.md.
client-workflow-bootstrap
Cursor rule "client-workflow-bootstrap" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, interview process and gate before generating.