Production-ready Claude Code configuration for full-stack Solana development. Combines best practices from multiple sources into an agent-optimized, token-efficient config you can install and adapt to your specific project.
> /plugin marketplace add solanabr/solana-ai-kit> /plugin install solana-ai-kit@stbr
Repo: solanabr/solana-ai-kit
What's inside
Production-ready Claude Code configuration for full-stack Solana development. Combines best practices from multiple sources into an agent-optimized, token-efficient config you can install and adapt to your specific project.
The idea here is to provide a generic CLAUDE.md that relies on subagents to plan and execute actions, dynamically loading markdown files, saving tokens and context in the end of the day. This config fully leverages the official Claude Code config recommendations:
Current multi-agent workflow favors monorepos, so we use a single CLAUDE.md/config for the whole project while leveraging agents and context-specific skills to solve each step of builder flow.
If you installed manually, remember to rename ./CLAUDE-solana.md back to ./CLAUDE.md, as the current top-level CLAUDE.md file is focused on maintaining the repo itself.
A complete .claude/ configuration that turns Claude into a Solana development expert with:
# Option 0: Fork Template (Github UI)
claude -m "/cleanup" # then start claude code running /cleanup so top-level directory of your project isn't polluted
# Option 1: One-liner installer (Claude Code)
curl -fsSL https://aikit.superteam.codes | bash
# Fallback (or before the aikit.superteam.codes DNS is live): curl -fsSL https://raw.githubusercontent.com/solanabr/solana-ai-kit/main/install.sh | bash
# Option 2: One-liner installer (Codex, Opencode, everything else)
curl -fsSL https://aikit.superteam.codes | bash -s -- --agents
# Fallback (or before the aikit.superteam.codes DNS is live): curl -fsSL https://raw.githubusercontent.com/solanabr/solana-ai-kit/main/install.sh | bash -s -- --agents
# Option 3: Manual setup
git clone --recurse-submodules https://github.com/solanabr/solana-ai-kit.git
cp -r solana-ai-kit/.claude /path/to/your-project/
cp solana-ai-kit/CLAUDE-solana.md /path/to/your-project/CLAUDE.md
cd /path/to/your-project && git submodule update --init --recursive
# Option 4: Claude Code plugin (run inside Claude Code)
/plugin marketplace add solanabr/solana-ai-kit
/plugin install solana-ai-kit@stbr
# Commands then namespace as /solana-ai-kit:<name>. The plugin is the CORE kit
# (agents/commands/local skills/MCP/hooks); the curl one-liner (Option 1) is the
# FULL install, adding rules + permissions/sandbox + the 18 ext/ submodules.
# Details: see "Install as a Claude Code plugin" below.
# Start Claude Code
claude
--agents FlagPass --agents to install everything into .agents/ instead of .claude/. Same content, different directory name. Useful when .claude/ is already taken or for non-Claude AI tools (Cursor, Windsurf, Copilot, etc.).
bash install.sh --agents /path/to/your-project
To update an --agents install:
# Run from your project root:
bash .agents/bin/update.sh
To keep your project clean, the installer adds .claude/, CLAUDE.md, .mcp.json, and .gitmodules to .gitignore — the kit reads as ignorable infrastructure, not your app code (the ext/ skill submodules are ignored too, re-fetched via git submodule update).
Want the config tracked in git (team setup, reproducible config)? Run /commit-claude-config — it un-ignores those files and commits them (or edit .gitignore by hand). If your project already commits .claude/ or its own .gitmodules, the new ignore lines are a no-op — git keeps tracking files it already tracks.
After installation, configure MCP servers for enhanced capabilities:
# In your project with Claude Code running:
/setup-mcp
This guides you through API key configuration for Helius, Context7, and other MCP servers.
solana-ai-kit is also its own Claude Code marketplace serving one core plugin. From inside Claude Code:
/plugin marketplace add solanabr/solana-ai-kit
/plugin install solana-ai-kit@stbr
The plugin ships the core kit: the 15 agents, 30 commands, the local go-to-market + registry skills (idea-sprint, pitch-deck, hackathon), the 7 MCP servers, and the dev hooks (banner, formatter, pre-deploy/commit gates). Commands and skills are namespaced — /deploy becomes /solana-ai-kit:deploy.
What the plugin cannot carry (Claude Code plugins are plain git clones — they can't init submodules or ship a permissions/sandbox policy), so these stay exclusive to the full install (install.sh):
.claude/rules/* code-style law (Rust, Anchor, Pinocchio, TypeScript, .NET)ext/ skill submodules (protocol, security, infra, ecosystem depth)For protocol-skill depth in plugin form, add the upstream marketplaces instead (routing, not copying) — e.g. /plugin marketplace add sendaifun/skills, ghostsecurity/skills, trailofbits/skills, cloudflare/skills. The plugin's skill hub and skill-registry.json list the current targets.
The two paths are complementary: individuals wanting Solana agents/commands across all their projects → plugin at user scope; project teams working in one repo → install.sh (full kit). If you enable both in the same project, /doctor warns about duplicate commands/hooks/MCP and advises picking one. Plugin auto-update is off by default for third-party marketplaces — refresh with /plugin marketplace update + claude plugin update.
| Submodule | Source | Purpose |
|---|---|---|
ext/solana-dev | solana-foundation/solana-dev-skill | Core Solana development (programs, frontend, testing, security) |
ext/sendai | sendaifun/skills | DeFi protocol integrations (Jupiter, Raydium, Kamino, perps, cross-chain, oracles, etc.) |
ext/solana-game | solanabr/solana-game-skill | Game development (Unity, PlaySolana, PSG1) |
ext/cloudflare | cloudflare/skills | Infrastructure (Workers, Agents SDK, MCP servers) |
ext/trailofbits | trailofbits/skills | Security auditing and vulnerability scanning |
ext/qedgen | QEDGen/solana-skills | Formal verification with Lean 4 theorem proving |
ext/solana-mobile | solana-mobile/solana-mobile-dev-skill | Mobile Wallet Adapter, Genesis Token, SKR address resolution |
ext/colosseum | ColosseumOrg/colosseum-copilot | Startup research, idea validation, hackathon projects |
ext/safe-solana-builder | frankcastleauditor/safe-solana-builder | Security-first code generation (70+ audit-derived rules) |
ext/vercel | vercel-labs/agent-skills | Vercel deployment, Next.js, AI SDK, v0, edge functions |
ext/solana-new | sendaifun/solana-new | 32 idea→launch journey skills + idea datasets/knowledge base; routed via local wrappers |
ext/ghostsecurity | ghostsecurity/skills | 7 AppSec skills: SAST criteria, SCA, secrets, validation |
ext/defending-code | anthropics/defending-code-reference-harness | Anthropic vuln-discovery reference harness + 6 skills |
ext/jupiter | jup-ag/agent-skills | Official Jupiter skills: Ultra swap, Lend, swap migration, VRFD |
ext/metaplex | metaplex-foundation/skill | Official Metaplex: Core, Token Metadata, Bubblegum, Candy Machine, Genesis |
ext/helius | helius-labs/core-ai | Official Helius infra skill + unique SVM internals skill |
ext/quicknode-anchor | quiknode-labs/solana-anchor-claude-skill | Anchor/financial-math/Quasar reference files (quarantined — refs only) |
ext/eth-to-sol | solana-foundation/eth-to-sol-skill | EVM/Solidity → Anchor two-pass porting |
Each agent loads its own specialized context on invocation:
"Use solana-architect to design the vault program"
"Use anchor-engineer to implement the deposit instruction"
"Use defi-engineer to integrate Jupiter swaps"
"Use solana-qa-engineer to write comprehensive tests"
Claude will spawn each specialized agent by itself based on context and, with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS enabled, orchestrate multi-agent workflows:
"Create an agent team: solana-architect for design, anchor-engineer for implementation, solana-qa-engineer for testing"
Recommended team patterns:
| Pattern | Flow | Use Case |
|---|---|---|
| program-ship | architect → anchor/pinocchio → qa | Build program from spec to tested |
| full-stack | architect → anchor → frontend → qa | End-to-end feature |
| audit-and-fix | qa → trailofbits context → anchor | Audit and remediate |
| game-ship | game-architect → unity → qa | Game feature |
| defi-compose | researcher → defi-engineer → qa | DeFi integration |
| token-launch | token-engineer → frontend → qa | Token creation + launch UI |
Pre-configured MCP servers in .mcp.json (API keys go in .env):
| Server | Capabilities |
|---|---|
| Helius | 60+ tools: RPC, DAS API, webhooks, priority fees, token metadata, NFT data |
| solana-dev | Solana Foundation official MCP — Solana docs, guides, and API references |
View @solanabr’s profileProduction-grade security audit for any codebase, powered by AI agents. 20 checklists · 1,413 verification items · 136 known attack vectors · executable PoCs + fix patches A full audit-firm lifecycle (automated + interactive) · Benchmarked against CertiK, SOC
@solanabrFAQ
solana-ai-kit is a Claude Code plugin with 3 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes hackathon, idea-sprint, pitch-deck. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it