solana

solana is a skill for Claude Code from ChainGPT-org/chaingpt-claude-skill. It costs 57 tokens per session (1,399 once invoked), scanned A, original, MIT.

A foundation for creating unsigned Solana transfers, including SOL and SPL tokens, which are assets on the Solana blockchain.

In plain words
What is it for?
It is for building base64-encoded transfers, deriving recipient token accounts, supporting Token-2022 assets, and preparing transactions for external signing.
Why use it?
It keeps private keys outside the tool and lets the user review and sign the generated transaction in a wallet such as Phantom, Backpack, Solflare, or a hardware wallet.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the chaingpt plugin — 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server shipped together

Good fit It is for building base64-encoded transfers, deriving recipient token accounts, supporting Token-2022 assets, and preparing transactions for external signing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chaingpt-org/chaingpt-claude-skill/solana
Install

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.

Any agent
npx skills add ChainGPT-org/chaingpt-claude-skill --skill solana
Clone the repo
git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skill

Made for: Claude Code.

Or install chaingpt, the plugin that ships this one along with the rest of its 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server.

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 solana

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/solana"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/solana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,399 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 $0.00057 $0.01399
Opus 5.5 $0.00023 $0.00560
Sonnet 5.5 $0.00011 $0.00280
Haiku 4.5 $0.00006 $0.00140

Measured 1mo ago against content hash 23736aeb23ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

skills/solana/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solana signing

This skill exposes a small foundation for building unsigned Solana transactions from chat. The plugin never sees a Solana private key — every state-changing tool returns a base64-encoded VersionedTransaction that the user signs in their wallet.

When to use this skill

  • The user asks to "send SOL to X" or "transfer USDC to Y" from a Solana address they control.
  • The user wants to inspect a Solana transaction someone else built before signing it.
  • A more advanced Solana flow (Drift order, Marginfi deposit, Kamino borrow) builds on the foundation here — when those land, they will reuse lib/solana-sign.ts directly.

What the surface is

  • chaingpt_solana_build_transfer_tx — build an unsigned transfer.
    • Native SOL when mint is omitted. Decimals: 9 (LAMPORTS_PER_SOL).
    • SPL Token (classic or Token-2022) when mint is provided. Decimals fetched from the mint account. Source + destination Associated Token Accounts derived automatically. Idempotent CreateATAIdempotent instruction included so first-time-recipient transfers work without an extra setup step.
    • acknowledgeMainnet: true required when network=mainnet. Same gate as the EVM tools.
  • chaingpt_solana_decode_tx — decode an unsigned base64 versioned transaction for review (payer, blockhash, instruction count, program ids with annotations).

Custody model

Identical to the rest of the plugin: custody-free. The plugin builds the transaction; the user signs it elsewhere. There is no MCP tool that accepts a secretKey, mnemonic, or seedPhrase parameter, and a unit test asserts this surface contract so future additions cannot accidentally break it.

If the user wants policy-gated signing (agent wallet pattern), the existing agent wallet skill provides that for EVM. A Solana counterpart is queued as a follow-up to this foundation.

Mainnet safety gate

When network=mainnet, the build tool refuses unless acknowledgeMainnet=true is also passed. The refusal message lists what to verify before re-call (recipient address, amount, mint, network). This matches feedback_mainnet_default: mainnet is the target, but mainnet transactions require an explicit ack.

Read the full file on GitHub · 97 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. 1mo ago First seen · 97 lines · 57 tokens per session scan A 23736aeb23ac

Subscribe to this mod's changes

solana is a skill published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (7 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,399 once invoked, about $0.0002 per session on Opus 5.5. 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.