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.
git 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/solana-transaction-safety)<a href="https://agentmods.dev/rules/helius-labs/core-ai/solana-transaction-safety"><img src="https://agentmods.dev/badge/rules/helius-labs/core-ai/solana-transaction-safety/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/rules/helius-labs/core-ai/solana-transaction-safety"><img src="https://agentmods.dev/badge/rules/helius-labs/core-ai/solana-transaction-safety.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 | $0.00390 | $0.00390 |
| Opus 5 | $0.00195 | $0.00195 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
solana-transaction-safety 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 10d 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
Transaction Submission
- ALWAYS submit transactions via Helius Sender endpoints — never raw
sendTransactionto standard RPC - ALWAYS include
skipPreflight: trueandmaxRetries: 0when using Sender - ALWAYS include a Jito tip instruction (minimum 0.0002 SOL) for dual routing
- ALWAYS include
ComputeBudgetProgram.setComputeUnitPrice— usegetPriorityFeeEstimateMCP tool, never hardcode fees - ALWAYS include
ComputeBudgetProgram.setComputeUnitLimit— simulate first to get actual CU usage, add 10% margin; never leave the default 200,000 CU limit - Instruction ordering: CU limit first, CU price second, your instructions, Jito tip last
Browser Safety
- From the browser, use the HTTPS Sender endpoint:
https://sender.helius-rpc.com/fast - NEVER use regional HTTP Sender endpoints from the browser — CORS preflight will fail
- For WebSocket data, use a server relay — never open Helius WebSockets directly from the browser (API key exposed in URL)
Commitment Levels
- Use
confirmedby default - Use
finalizedfor critical operations that can wait seconds for confirmation - Never rely on
processedfor anything important
Phantom Wallet Signing
- For extension wallets (
"injected"provider): usesignTransactionthen submit via Helius Sender - For embedded wallets (
"google","apple"providers): usesignAndSendTransaction—signTransactionis NOT supported - NEVER auto-approve transactions — each must be explicitly approved by the user
- ALWAYS handle user rejection gracefully — this is not an error to retry
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.
- 10d ago First seen · 34 lines · 390 tokens per session scan A 6a2927aebdbd
solana-transaction-safety is a cursor rule published in the GitHub repository helius-labs/core-ai (26 stars, last pushed 6d ago), licensed MIT. It adds 390 tokens to every session, about $0.0019 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.
Other cursor rules, from other repositories
nextjs-react-typescript-cursorrules-prompt-file
Cursor rules for Next.js development with React and TypeScript integration.
solidity-react-blockchain-apps-cursorrules-prompt-
Cursor rules for Solidity development with React Blockchain apps integration.
nextjs
Rules for Next.js projects (App Router and Pages Router).
react
Rules for React component files (any framework).
wagmi
Cursor rule "wagmi" from devridge0/basilic-evm, covering wagmi v2 best practices, hooks and state management rules, account connection, smart contract interaction rules and reading from contracts.
react-typescript-frontend
Frontend development standards for React TypeScript projects with modern tooling.