solana-agent-kit: Instructions file for Claude Code

CLAUDE.md

solana-agent-kit CLAUDE.md is an instructions file for Claude Code from sendaifun/solana-agent-kit. It costs 1,045 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for a pnpm monorepo, a single codebase containing multiple related packages, that builds AI agents for Solana, a blockchain platform.

In plain words
What is it for?
Use it to build all packages or a specific plugin, run linting and formatting, test the project, generate documentation, or clean build files.
Why use it?
It records the required Node.js and pnpm versions, package layout, and commands, reducing mistakes when installing dependencies, testing, or building one package.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is sendaifun/solana-agent-kit's own configuration. It tells Claude Code how to work on solana-agent-kit 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 solana-agent-kit configures →

About the project

Solana Agent Kit is an open-source toolkit that lets AI agents interact with Solana protocols and perform blockchain actions. Developers use it to build agents that trade and transfer tokens, create NFTs, use DeFi services, bridge assets, and carry out other Solana operations.

sendaifun/solana-agent-kit · 1,709 stars · on GitHub · kit.sendai.fun

Reuse

Borrowing it

Nothing to install: this file belongs to sendaifun/solana-agent-kit. 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/sendaifun/solana-agent-kit/v2/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sendaifun/solana-agent-kit

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 solana-agent-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sendaifun/solana-agent-kit/claude-md/github.svg)](https://agentmods.dev/instructions/sendaifun/solana-agent-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sendaifun/solana-agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/sendaifun/solana-agent-kit/claude-md/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-agent-kit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sendaifun/solana-agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/sendaifun/solana-agent-kit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,045 This file is loaded in full into every session.
When invoked 1,045 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01045 $0.01045
Opus 5 $0.00522 $0.00522
Sonnet 5 $0.00209 $0.00209
Haiku 4.5 $0.00104 $0.00104

Measured 9d ago against content hash eefd238b70e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

solana-agent-kit CLAUDE.md 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Development Commands

# Install dependencies (requires pnpm 9+, Node 22+)
pnpm install

# Build all packages
pnpm run build

# Build specific packages
pnpm run build:core              # Core package only
pnpm run build:plugin-token      # Token plugin
pnpm run build:plugin-defi       # DeFi plugin
pnpm run build:plugin-nft        # NFT plugin
pnpm run build:plugin-misc       # Misc plugin
pnpm run build:plugin-blinks     # Blinks plugin
pnpm run build:adapter-mcp       # MCP adapter

# Lint and format
pnpm run lint                    # Check with Biome
pnpm run lint:fix                # Auto-fix lint issues
pnpm run format                  # Format code with Biome

# Run tests (interactive - prompts for "agent" or "programmatic" mode)
# Requires OPENAI_API_KEY, RPC_URL, SOLANA_PRIVATE_KEY in test/.env
pnpm run test

# Generate documentation
pnpm run docs

# Clean all build artifacts
pnpm run clean

Architecture Overview

This is a monorepo using pnpm workspaces and Turborepo for building AI agents that interact with Solana protocols.

Package Structure

packages/
├── core/           # solana-agent-kit - Main SDK with SolanaAgentKit class
├── plugin-token/   # Token operations (transfers, swaps, Jupiter, PumpFun)
├── plugin-defi/    # DeFi protocols (Drift, Orca, Raydium, Meteora, etc.)
├── plugin-nft/     # NFT operations (Metaplex, 3Land)
├── plugin-misc/    # Utilities (CoinGecko, Allora, domains, webhooks)
├── plugin-blinks/  # Solana Blinks (arcade games)
└── adapter-mcp/    # Model Context Protocol server adapter

Core Concepts

Plugin System: V2 uses a composable plugin architecture. Plugins register methods (direct function calls) and actions (AI agent tools with schemas).

// Plugin structure
interface Plugin {
  name: string;
  methods: Record<string, Function>;  // Programmatic API
  actions: Action[];                   // AI agent tools with Zod schemas
  initialize(agent: SolanaAgentKit): void;
}

// Action structure for AI tools
interface Action {
  name: string;
  similes: string[];           // Alternative trigger phrases
  description: string;
  examples: ActionExample[][];
  schema: z.ZodType<any>;      // Input validation
  handler: Handler;            // Execution function
}

Read the full file on GitHub · 129 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. 9d ago First seen · 129 lines · 1,045 tokens per session scan A eefd238b70e2

Subscribe to this mod's changes

solana-agent-kit CLAUDE.md is an instructions file published in the GitHub repository sendaifun/solana-agent-kit (1,709 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,045 tokens to every session, about $0.0052 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens