core-ai
AGENTS.md0 starsChanged 8 months agoMITView on GitHub
This file is the Layer A harness for Codex CLI and other OpenAI-compatible agents. Skills in .agents/skills/ provide the domain expertise (Layer B). This monorepo contains Helius developer tools for building on Solana: The Helius MCP server provides live blockchain access through 10 public tools total: 9 routed domain tools plus expandResult. Configure it as an MCP tool source: This works with any MCP-compatible client. Use a domain tool such as heliusWallet, heliusAsset, or heliusStreaming plus action: "getBalance", action: "getAssetsByOwner",…
- Reads credentials
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- helius-cli/CLAUDE.mdCLAUDE.md
- helius-mcp/CLAUDE.mdCLAUDE.md
- helius-dflowSkill
- helius-okxSkill
- helius-phantomSkill
- heliusSkill
- svmSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
20 rules. About 0 are common, 4 are distinctive, and 16 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
16
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 54
Path B — Agentic signup: Call generateKeypair → fund the wallet with ~0.001 SOL + 1 USDC → checkSignupBalance → agenticSignup.
- Very specific: line 101
Never commit API keys to git — use HELIUS_API_KEY environment variable
- Very specific: line 105
Always use Orb (https://orbmarkets.io) for transaction and account links
- Very specific: line 113
Use heliusWallet + getBalance (1 credit) over heliusWallet + getWalletBalances (100 credits) when only SOL balance is needed
- Very specific: line 114
Use heliusWallet + getTokenBalances (10 credits) over heliusWallet + getWalletBalances when you don't need USD values
- Very specific: line 115
Use heliusKnowledge + lookupHeliusDocs with the section parameter for targeted lookups — full docs can be 10,000+ tokens
- Very specific: line 123
Always use Helius Sender endpoints — never raw sendTransaction to standard RPC
- Very specific: line 124
Always include skipPreflight: true when using Sender
- Distinctive: line 126
Always include a Jito tip (minimum 0.0002 SOL) and priority fee
- Very specific: line 127
Use heliusChain + getPriorityFeeEstimate to get fee levels — never hardcode fees
- Very specific: line 130
Use heliusTransaction + parseTransactions over raw RPC for human-readable transaction data
- Very specific: line 131
Use heliusAsset + getAssetsByOwner with showFungible: true for both NFTs and fungible tokens
- Very specific: line 132
Use heliusAsset + searchAssets for multi-criteria queries instead of client-side filtering
- Very specific: line 135
Use heliusKnowledge + troubleshootError with the error code before manual diagnosis
- Very specific: line 136
Use heliusKnowledge + getRateLimitInfo or getHeliusCreditsInfo — never guess at credit costs
- Distinctive: line 141
Use MCP tools for live blockchain data — never hardcode or mock chain state
- Distinctive: line 142
Read reference files before writing code — they contain product-specific patterns and pitfalls
- Distinctive: line 143
Run tests and verify outputs after making changes
- Very specific: line 145
Use appropriate commitment levels (confirmed for reads, finalized for critical operations)
- Very specific: line 154
Do not edit these directly — modify the canonical source in helius-skills/ and re-run the compiler.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Core AI — Agent Instructions
This file is the Layer A harness for Codex CLI and other OpenAI-compatible agents. Skills in
.agents/skills/provide the domain expertise (Layer B).
Repository Overview
This monorepo contains Helius developer tools for building on Solana:
| Package | What it does |
helius-mcp/ | MCP server (npx helius-mcp@latest) — exposes 10 public tools total: 9 routed domain tools plus expandResult |
helius-skills/ | Canonical skill source — SKILL.md + reference files for each domain |
helius-plugin/ | Claude Code plugin — bundles skills + auto-starts MCP server |
helius-cli/ | CLI for account setup, blockchain queries, and staking (npx helius-cli@latest) |
MCP Server Setup
The Helius MCP server provides live blockchain access through 10 public tools total: 9 routed domain tools plus expandResult. Configure it as an MCP tool source:
npx helius-mcp@latestThis works with any MCP-compatible client. Use a domain tool such as heliusWallet, heliusAsset, or heliusStreaming plus action: "getBalance", action: "getAssetsByOwner", or action: "createWebhook" to call a specific Helius action. Use expandResult for summary-first follow-ups.
For Codex, run codex mcp add helius -- npx helius-mcp@latest or add to .codex/config.toml (or ~/.codex/config.toml for global):
[mcp_servers.helius]
command = "npx"
args = ["helius-mcp@latest"]For other MCP clients, add to your project's .mcp.json:
{
"mcpServers": {
"helius": {
"command": "npx",
"args": ["helius-mcp@latest"]
}
}
}API Key Setup
Most tools require a Helius API key. Three paths:
Path A — Existing key: Set the HELIUS_API_KEY environment variable, or call the setHeliusApiKey MCP tool.
Path B — Agentic signup: Call generateKeypair → fund the wallet with ~0.001 SOL + 1 USDC → checkSignupBalance → agenticSignup. The API key is configured automatically.
Path C — CLI: npx helius-cli@latest keygen → fund wallet → npx helius-cli@latest signup
Get keys from https://dashboard.helius.dev.
Public Tool Surface
Helius MCP exposes 10 public tools total:
- Routed domain tools:
heliusAccount,heliusWallet,heliusAsset,heliusTransaction,heliusChain,heliusStreaming,heliusKnowledge,heliusWrite,heliusCompression - Expansion tool:
expandResult
The routed domain tools take a Helius action name in action. Example:
heliusWallet+action: "getBalance"heliusKnowledge+action: "getRateLimitInfo"heliusStreaming+action: "createWebhook"
Heavy responses are summary-first. Use expandResult({ resultId: "..." }) to fetch a full section, range, page, or continuation on demand.
Skills
Skills are in .agents/skills/. Each provides expert routing, rules, and reference docs for a domain:
| Skill | Directory | When to use |
| Helius | .agents/skills/helius/ | Building Solana apps with Helius infrastructure — transactions, DAS API, WebSockets, Laserstream, webhooks, wallet analysis |
| Helius DFlow | .agents/skills/helius-dflow/ | Trading apps combining DFlow (spot swaps, prediction markets, Proof KYC) with Helius |
| Helius Phantom | .agents/skills/helius-phantom/ | Frontend Solana apps with Phantom wallet + Helius — React, React Native, vanilla JS |
| SVM | .agents/skills/svm/ | Solana protocol internals — SVM engine, account model, consensus, validators, token extensions |
Each skill has:
SKILL.md— routing logic, rules, and domain expertisereferences/— deep reference docs for specific products/APIsprompts/— pre-formatted prompt variants for OpenAI API and Claude API
Read the SKILL.md before implementing — it tells you which reference files to read and which MCP tools to use for each type of task.
Coding Conventions
SDK Usage
- TypeScript:
import { createHelius } from "helius-sdk"→const helius = createHelius({ apiKey: "apiKey" }) - Rust:
use helius::Helius→Helius::new("apiKey", Cluster::MainnetBeta)? - For
@solana/kitintegration, usehelius.rawfor the underlyingRpcclient
Environment Variables
- Never commit API keys to git — use
HELIUS_API_KEYenvironment variable - Store keys in
.envor.env.local(for Next.js, neverNEXT_PUBLIC_)
Explorer Links
- Always use Orb (
https://orbmarkets.io) for transaction and account links - Transaction:
https://orbmarkets.io/tx/{signature} - Account:
https://orbmarkets.io/address/{address} - Token:
https://orbmarkets.io/token/{token}
MCP Tool Usage Rules
Prefer Specific Routed Actions
- Use
heliusWallet+getBalance(1 credit) overheliusWallet+getWalletBalances(100 credits) when only SOL balance is needed - Use
heliusWallet+getTokenBalances(10 credits) overheliusWallet+getWalletBalanceswhen you don't need USD values - Use
heliusKnowledge+lookupHeliusDocswith thesectionparameter for targeted lookups — full docs can be 10,000+ tokens
Use Batch Endpoints
heliusAsset+getAssetaccepts anidsarray for batch lookups — one call instead of NheliusAsset+getAssetProofBatchfor multiple compressed NFT proofsheliusChain+getAccountInfoaccepts anaddressesarray for batch account lookups
Transaction Sending
- Always use Helius Sender endpoints — never raw
sendTransactionto standard RPC - Always include
skipPreflight: truewhen using Sender - Always include
maxRetries: 0when using Sender - Always include a Jito tip (minimum 0.0002 SOL) and priority fee
- Use
heliusChain+getPriorityFeeEstimateto get fee levels — never hardcode fees
Data Queries
- Use
heliusTransaction+parseTransactionsover raw RPC for human-readable transaction data - Use
heliusAsset+getAssetsByOwnerwithshowFungible: truefor both NFTs and fungible tokens - Use
heliusAsset+searchAssetsfor multi-criteria queries instead of client-side filtering
Errors and Docs
- Use
heliusKnowledge+troubleshootErrorwith the error code before manual diagnosis - Use
heliusKnowledge+getRateLimitInfoorgetHeliusCreditsInfo— never guess at credit costs - For pricing questions, start with
heliusAccount+getHeliusPlanInfo— notheliusKnowledge+lookupHeliusDocs
Agent Behavior
- Use MCP tools for live blockchain data — never hardcode or mock chain state
- Read reference files before writing code — they contain product-specific patterns and pitfalls
- Run tests and verify outputs after making changes
- Handle rate limits with exponential backoff
- Use appropriate commitment levels (
confirmedfor reads,finalizedfor critical operations)
Generated Content
The following directories are generated by npx tsx scripts/compile-skills.ts from canonical sources in helius-skills/:
.agents/skills/— Codex-native skills + prompt variantshelius-mcp/system-prompts/— npm-shipped prompt copies
Do not edit these directly — modify the canonical source in helius-skills/ and re-run the compiler.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

