Release Rebase
jito-foundation/geyser-grpc-plugin
A skill your agent uses when updating this repo to match a new jito-solana release line such as v4.0.
Direct Solana blockchain interaction via JSON-RPC — account lookups, token balances, transaction submission, and program queries
$ npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agiprolabs/claude-trading-skills solana-rpc --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/solana-rpc .claude/skills/solana-rpc && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "solana-rpc" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/solana-rpc into .claude/skills/solana-rpc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solana-rpc", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/solana-rpcType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agiprolabs/claude-trading-skills solana-rpc --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/solana-rpc .agents/skills/solana-rpc && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "solana-rpc" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/solana-rpc into .agents/skills/solana-rpc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solana-rpc", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agiprolabs/claude-trading-skills solana-rpc --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/solana-rpc .cursor/skills/solana-rpc && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "solana-rpc" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/solana-rpc into .cursor/skills/solana-rpc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solana-rpc", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agiprolabs/claude-trading-skills.git --path skills/solana-rpc--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agiprolabs/claude-trading-skills solana-rpc --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/solana-rpc .gemini/skills/solana-rpc && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "solana-rpc" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/solana-rpc into .gemini/skills/solana-rpc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solana-rpc", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agiprolabs/claude-trading-skills solana-rpcInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/solana-rpc .github/skills/solana-rpc && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "solana-rpc" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/solana-rpc into .github/skills/solana-rpc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solana-rpc", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agiprolabs/claude-trading-skills solana-rpc --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/solana-rpc .opencode/skills/solana-rpc && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "solana-rpc" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/solana-rpc into .opencode/skills/solana-rpc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "solana-rpc", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
solana-rpcDirect Solana blockchain interaction via JSON-RPC — account lookups, token balances, transaction submission, and program queries
Solana Rpc is an agent skill from agiprolabs/claude-trading-skills. Direct Solana blockchain interaction via JSON-RPC — account lookups, token balances, transaction submission, and program queries
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/error_handling.md`, `references/methods.md` and `references/providers.md`).
It sits in Backend & APIs, covering gRPC and Protobuf. It works with Solana. The repository describes itself as: 68 trading, DeFi, and quantitative finance Agent Skills. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ other tools. The licence is MIT.
Read from SKILL.md and the folder at commit 981e1d7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.mainnet-beta.solana.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Solana Rpc loads about 2.3k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 35 tokens; SKILL.md has 344 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from agiprolabs/claude-trading-skills at commit 981e1d7, republished under its MIT licence (© agiprolabs). 344 words, ~2,281 tokens.
.claude/skills/solana-rpc/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.The Solana JSON-RPC API provides direct read/write access to the blockchain. Use it for account state queries, token balance lookups, transaction building and submission, and program account enumeration. This is the low-level foundation when higher-level APIs (Birdeye, Helius, SolanaTracker) don't have the data you need.
import httpx
RPC = os.getenv("SOLANA_RPC_URL", "https://api.mainnet-beta.solana.com")
def rpc_call(method: str, params: list = None) -> dict:
resp = httpx.post(RPC, json={
"jsonrpc": "2.0", "id": 1,
"method": method, "params": params or [],
}, timeout=30.0)
return resp.json()
# Get SOL balance
result = rpc_call("getBalance", ["WALLET_PUBKEY"])
sol_balance = result["result"]["value"] / 1e9
# Get latest blockhash
result = rpc_call("getLatestBlockhash")
blockhash = result["result"]["value"]["blockhash"]| Provider | Free Tier | Paid | Notes |
|---|---|---|---|
| Helius | 50K credits/day | $49+/mo | Enhanced RPCs, DAS API |
| QuickNode | Limited | $49+/mo | Multi-chain, WebSocket |
| Triton | No free tier | ~$300+/mo | Yellowstone gRPC bundled |
| Shyft | Limited | $49+/mo | Yellowstone gRPC bundled |
| Alchemy | 300M CU/mo | Scaling | Good free tier |
| Public (mainnet-beta) | Free | — | Rate limited, unreliable |
Recommendation: Use Helius or QuickNode for development. Never use public RPC for production trading.
# SOL balance (in lamports, divide by 1e9 for SOL)
getBalance(pubkey, {commitment: "confirmed"})
# Full account info (data, owner, lamports, executable)
getAccountInfo(pubkey, {encoding: "jsonParsed"})
# Multiple accounts in one call
getMultipleAccounts([pubkey1, pubkey2], {encoding: "jsonParsed"})# All SPL token accounts owned by a wallet
getTokenAccountsByOwner(wallet_pubkey, {
"programId": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA"
}, {"encoding": "jsonParsed"})
# Token balance for a specific token account
getTokenAccountBalance(token_account_pubkey)
# Largest token accounts (top holders)
getTokenLargestAccounts(mint_pubkey)
# Total supply of a token
getTokenSupply(mint_pubkey)# Get parsed transaction by signature
getTransaction(signature, {
"encoding": "jsonParsed",
"maxSupportedTransactionVersion": 0,
})
# Recent transaction signatures for an address
getSignaturesForAddress(pubkey, {
"limit": 20,
"before": "optional_signature", # pagination cursor
})
# Transaction status
getSignatureStatuses([sig1, sig2])# Current slot
getSlot({commitment: "confirmed"})
# Block data
getBlock(slot, {
"encoding": "jsonParsed",
"transactionDetails": "full",
"maxSupportedTransactionVersion": 0,
})
# Latest blockhash (needed for tx building)
getLatestBlockhash({commitment: "confirmed"})
# Slot leader schedule
getLeaderSchedule()# All accounts owned by a program (with filters)
getProgramAccounts(program_pubkey, {
"encoding": "jsonParsed",
"filters": [
{"dataSize": 165}, # Filter by account data size
{"memcmp": { # Filter by data content
"offset": 32,
"bytes": "base58_encoded_value",
}},
],
})Warning: getProgramAccounts without filters can return millions of results and timeout. Always use dataSize and/or memcmp filters.
# Recent priority fee estimates
getRecentPrioritizationFees([account_pubkey])
# Returns array of { slot, prioritizationFee } for recent slots
# Minimum rent for account
getMinimumBalanceForRentExemption(data_length)# Send a signed, serialized transaction
sendTransaction(base64_tx, {
"encoding": "base64",
"skipPreflight": False,
"preflightCommitment": "confirmed",
"maxRetries": 3,
})
# Simulate before sending
simulateTransaction(base64_tx, {
"encoding": "base64",
"sigVerify": False,
"commitment": "confirmed",
})import time
def confirm_transaction(rpc_url: str, signature: str, timeout: float = 30.0) -> bool:
"""Poll for transaction confirmation."""
start = time.time()
while time.time() - start < timeout:
result = rpc_call("getSignatureStatuses", [[signature]])
statuses = result.get("result", {}).get("value", [None])
if statuses[0] is not None:
status = statuses[0]
if status.get("err"):
return False
if status.get("confirmationStatus") in ("confirmed", "finalized"):
return True
time.sleep(0.5)
return False| Level | Description | Use When |
|---|---|---|
processed | Single node confirmation | Speed over safety |
confirmed | Supermajority (2/3+) | Default for trading |
finalized | Maximum supermajority + 31 slots | Critical operations |
Always specify commitment explicitly. Default varies by provider.
def get_wallet_tokens(wallet: str) -> list[dict]:
"""Get all SPL token holdings with metadata."""
result = rpc_call("getTokenAccountsByOwner", [
wallet,
{"programId": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA"},
{"encoding": "jsonParsed"},
])
tokens = []
for acct in result["result"]["value"]:
info = acct["account"]["data"]["parsed"]["info"]
tokens.append({
"mint": info["mint"],
"amount": int(info["tokenAmount"]["amount"]),
"decimals": info["tokenAmount"]["decimals"],
"ui_amount": info["tokenAmount"]["uiAmount"],
})
return [t for t in tokens if t["amount"] > 0]def get_top_holders(mint: str) -> list[dict]:
"""Get the 20 largest holders of a token."""
result = rpc_call("getTokenLargestAccounts", [mint])
supply_result = rpc_call("getTokenSupply", [mint])
total_supply = int(supply_result["result"]["value"]["amount"])
holders = []
for acct in result["result"]["value"]:
amount = int(acct["amount"])
holders.append({
"address": acct["address"],
"amount": amount,
"decimals": acct["decimals"],
"ui_amount": acct["uiAmount"],
"percentage": amount / total_supply * 100 if total_supply > 0 else 0,
})
return holdersdef rpc_batch(calls: list[tuple[str, list]]) -> list[dict]:
"""Execute multiple RPC calls in a single HTTP request."""
payload = [
{"jsonrpc": "2.0", "id": i, "method": method, "params": params}
for i, (method, params) in enumerate(calls)
]
resp = httpx.post(RPC, json=payload, timeout=30.0)
results = resp.json()
results.sort(key=lambda r: r["id"])
return [r.get("result") for r in results]| Program | ID |
|---|---|
| System | 11111111111111111111111111111111 |
| SPL Token | TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA |
| Token-2022 | TokenzQdBNbLqP5VEhdkAS6EPFLC1PHnBqCXEpPxuEb |
| Associated Token | ATokenGPvbdGVxr1b2hvZbsiqW5xWH25efTNsLJA8knL |
| Raydium AMM | 675kPX9MHTjS2zt1qfr1NYHuzeLXfQM9H24wFSUt1Mp8 |
| Raydium CLMM | CAMMCzo5YL8w4VFF8KVHrK22GGUsp5VTaW7grrKgrWqK |
| Orca Whirlpool | whirLbMiicVdio4qvUfM5KAg6Ct8VwpYzGff3uctyCc |
| Meteora DLMM | LBUZKhRxPF3XUpBCjp4YzTKgLccjZhTSDM9YuVaPwxo |
| PumpFun | 6EF8rrecthR5Dkzon8Nwu78hRvfCKubJ14M5uBEwF6P |
| Jupiter v6 | JUP6LkbZbjS1jKKwapdHNy74zcZ3tLUZoi5QNyVTaV4 |
| Compute Budget | ComputeBudget111111111111111111111111111111 |
| Need | Use |
|---|---|
| Token balance check | Direct RPC (getTokenAccountsByOwner) |
| Top 20 holders | Direct RPC (getTokenLargestAccounts) |
| Historical OHLCV | Birdeye or SolanaTracker |
| Parsed transaction history | Helius Enhanced Transactions |
| Token metadata (name, image) | Helius DAS API |
| Real-time streaming | Yellowstone gRPC |
| Wallet PnL tracking | SolanaTracker |
| Token risk scoring | SolanaTracker |
| Cross-chain data | DexScreener or CoinGecko |
references/methods.md — Complete RPC method reference with parameters and response schemasreferences/error_handling.md — Error codes, rate limits, timeout handling, retry strategiesreferences/providers.md — RPC provider comparison with pricing and featuresscripts/wallet_scanner.py — Scan wallet for all token holdings with balancesscripts/token_holders.py — Get top holders and concentration metrics for any token© agiprolabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (scripts, references) in skills/solana-rpc of agiprolabs/claude-trading-skills.
Open the folder on GitHubat commit 981e1d7
Solana Rpc next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Solana Rpc this skillagiprolabs/claude-trading-skills | 410 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Release Rebasejito-foundation/geyser-grpc-plugin | 145 | — | ~836 | Automated safety check: Pass | Custom licence | |
| Alchemy APImoonpay/skills | 113 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Quicknode Skillinternet-court/internet-court-skill | 6.6k | — | ~11k | Automated safety check: Pass | MIT | |
| Quicknodesendaifun/skills | 130 | 1 repos | ~5.5k | Automated safety check: Notes | Apache-2.0 | |
| Alchemy OfficialLeoYeAI/openclaw-master-skills | 2.2k | — | ~6.1k | Automated safety check: Pass | MIT |
jito-foundation/geyser-grpc-plugin
A skill your agent uses when updating this repo to match a new jito-solana release line such as v4.0.
moonpay/skills
Integrates Alchemy blockchain APIs using an API key. An agent skill from moonpay/skills.
internet-court/internet-court-skill
Quicknode blockchain infrastructure for 80+ chains: Core RPC API, Streams, Webhooks, Blazar WSS, Solana gRPC, HyperCore gRPC, SQL Explorer, Metaplex DAS API, Blockbook, Ordinals & Runes API, Swap…
sendaifun/skills
Quicknode blockchain infrastructure for Solana — RPC endpoints, DAS API (Digital Asset Standard) for NFTs and compressed assets, Yellowstone gRPC streaming, Priority Fee API, Streams (real-time data…
LeoYeAI/openclaw-master-skills
Official Alchemy skill. An agent skill from LeoYeAI/openclaw-master-skills.
mountain-loop/yaak
A skill your agent uses when the user mentions Yaak, a Yaak workspace, or the yaak command, or asks to call, hit, or smoke test HTTP/REST endpoints, save or organize API requests for reuse or manual…
agiprolabs/claude-trading-skills
Event-driven backtesting with bar-by-bar execution, complex order types, multiple analyzers, and custom indicators
agiprolabs/claude-trading-skills
Solana token market data via Birdeye — prices, OHLCV, trades, token metadata, security checks, and trader activity
agiprolabs/claude-trading-skills
Broad crypto market data from CoinGecko covering 13,000+ tokens.
agiprolabs/claude-trading-skills
Cointegration testing for pairs trading using Engle-Granger, Johansen, and rolling stability analysis
agiprolabs/claude-trading-skills
Wallet evaluation, monitoring, and copy-trade strategy design for Solana DEX trading
agiprolabs/claude-trading-skills
Cross-asset correlation analysis including rolling correlation, hierarchical clustering, tail dependence, and regime-dependent correlation
Works with
Categories
Direct Solana blockchain interaction via JSON-RPC — account lookups, token balances, transaction submission, and program queries. Solana Rpc is an agent skill from agiprolabs/claude-trading-skills.
Solana Rpc fits situations like: tasks that involve gRPC and Protobuf.
Run `npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a claude-code`. Or copy the skill folder (skills/solana-rpc in agiprolabs/claude-trading-skills) into .claude/skills/solana-rpc in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a codex`. Or copy the skill folder (skills/solana-rpc in agiprolabs/claude-trading-skills) into .agents/skills/solana-rpc in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agiprolabs/claude-trading-skills --skill solana-rpc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/solana-rpc, .gemini/skills/solana-rpc, .github/skills/solana-rpc and .opencode/skills/solana-rpc in your project.
Going by SKILL.md and its folder, Solana Rpc needs Python for the scripts in its folder. Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: api.mainnet-beta.solana.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Solana Rpc is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Solana Rpc: Release Rebase (jito-foundation/geyser-grpc-plugin, 145 stars), Alchemy API (moonpay/skills, 113 stars), Quicknode Skill (internet-court/internet-court-skill, 6.6k stars) and Quicknode (sendaifun/skills, 130 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agiprolabs (a GitHub user) maintains it in agiprolabs/claude-trading-skills, which has 410 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on September 3, 2026.
Source: agiprolabs/claude-trading-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.