orquestra: Skill for Claude Code

.claude/skills/orquestra-solana/SKILL.md

orquestra-solana is a skill for Claude Code from berkayoztunc/orquestra. It costs 133 tokens per session (1,544 once invoked), scanned A, original, MIT.

An end-to-end workflow for carrying out actions on Solana, a blockchain platform. It divides the work into research, account lookup, transaction building, simulation, and—after approval—signing and sending.

In plain words
What is it for?
It helps with tasks such as staking SOL, swapping tokens, minting assets, transferring funds, and using Solana programs built with Anchor.
Why use it?
It guides an agent through the required steps and checks before a transaction is submitted. Research-only requests can stop before anything is built or sent.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is berkayoztunc/orquestra's own configuration. It tells Claude Code how to work on orquestra itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orquestra configures →

Reuse

Borrowing it

Nothing to install: this file belongs to berkayoztunc/orquestra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/berkayoztunc/orquestra/main/.claude/skills/orquestra-solana/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/berkayoztunc/orquestra

Made for: Claude Code.

Wrote 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.

agentmods badge for orquestra-solana

README.md
[![agentmods](https://agentmods.dev/badge/skills/berkayoztunc/orquestra/orquestra-solana/github.svg)](https://agentmods.dev/skills/berkayoztunc/orquestra/orquestra-solana)
Your own site
<a href="https://agentmods.dev/skills/berkayoztunc/orquestra/orquestra-solana"><img src="https://agentmods.dev/badge/skills/berkayoztunc/orquestra/orquestra-solana/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.

agentmods 80×15 button for orquestra-solana

Your own site · 80×15
<a href="https://agentmods.dev/skills/berkayoztunc/orquestra/orquestra-solana"><img src="https://agentmods.dev/badge/skills/berkayoztunc/orquestra/orquestra-solana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,544 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00133 $0.01544
Opus 5 $0.00067 $0.00772
Sonnet 5 $0.00027 $0.00309
Haiku 4.5 $0.00013 $0.00154

Measured 12d ago against content hash 7b143f9882cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

orquestra-solana 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 12d 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/skills/orquestra-solana/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orquestra Solana Pipeline

The Orquestra agent pipeline executes Solana tasks end-to-end in 4 stages. Each stage is a specialized sub-agent. The orquestra orchestrator manages them.

Pipeline Overview

User intent
    │
    ▼
[1] orquestra-researcher   — find program, list instructions + PDAs
    │
    ▼
[2] orquestra-pda-explorer — derive PDAs, resolve all required accounts
    │
    ▼
[3] orquestra-tx-builder   — build unsigned base64 wire transaction
    │
    ▼
[3.5] orquestra-simulator  — preflight: compute units, Anchor error decode
    │
    ▼ (user confirms)
[4] orquestra-signer       — sign + send, explicit YES required

How to Start

Say the task in plain English to the orquestra orchestrator:

"Stake 2 SOL with Marinade for wallet 9xTy...pQr2" "Swap 1 SOL to USDC on Jupiter" "Derive the stake account PDA for Marinade" "What instructions does the Kamino lending program have?"

The orchestrator decides which stages to run. Research-only tasks stop at Stage 1.


Stage 1 — Research (orquestra-researcher)

What it does: searches the Orquestra registry, reads docs, lists instructions and PDA schemas.

MCP tools used: search_programs, read_llms_txt, list_instructions, list_pda_accounts, get_ai_analysis

What you get back:

  • Program name + projectId
  • All instructions (name, args, accounts)
  • All PDA account types + seed schemas

You only need to provide: program name or keyword (e.g. "Marinade", "Jupiter", "Kamino")


Stage 2 — Account Resolution (orquestra-pda-explorer)

What it does: derives every PDA address required by the instruction.

MCP tools used: list_pda_accounts, derive_pda, fetch_pda_data (via Orquestra MCP)

What you need to provide:

  • Your wallet public key (fee payer / authority / signer)
  • Any token mint addresses if the instruction requires them
  • Any other user-provided seeds (amounts are NOT seeds)

What the agent resolves automatically:

  • All PDAs derivable from your wallet + known program constants
  • Nested PDAs (fetches on-chain data to extract further addresses)

Read the full file on GitHub · 180 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. 12d ago First seen · 180 lines · 133 tokens per session scan A 7b143f9882cc

Subscribe to this mod's changes

orquestra-solana is a skill published in the GitHub repository berkayoztunc/orquestra (23 stars, last pushed 25d ago), licensed MIT. It adds 133 tokens to every session and 1,544 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

nansen-dca-tracker

What tokens are whales dollar-cost averaging into? Jupiter DCA strategies by smart money and target token fundamentals.

moonpay/skills · 28 tokens

x402

Build internet-native payments with x402 - HTTP 402 for on-chain micropayments, no accounts or API keys. Use for paid APIs, paywalled content, agent payment flows, or per-call MCP tools. TypeScript, Python, and Go SDKs across EVM and Solana.

tenequm/skills · 63 tokens

metengine-data-agent

Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.

sendaifun/skills · 57 tokens

meteora

Complete Meteora DeFi SDK suite for building liquidity pools, AMMs, bonding curves, vaults, token launches, and zap operations on Solana. Use when integrating DLMM, DAMM v2, DAMM v1, Dynamic Bonding Curves, Alpha Vaults, Zap, or Stake-for-Fee functionality.

sendaifun/skills · 69 tokens

kamino

Complete guide for Kamino Finance - Solana's leading DeFi protocol for lending, borrowing, liquidity management, and leverage trading. Covers klend-sdk (lending), kliquidity-sdk (automated liquidity strategies), scope-sdk (oracle aggregator), multiply/leverage operations, vaults, and obligation orders.

sendaifun/skills · 65 tokens

coingecko

Complete CoinGecko Solana API integration for token prices, DEX pool data, OHLCV charts, trades, and market analytics. Use for building trading bots, portfolio trackers, price feeds, and on-chain data applications.

sendaifun/skills · 50 tokens