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.
npx skills add demo112/yunqu-ai-skills --skill 11-solana-agent-buildergit clone --depth 1 https://github.com/demo112/yunqu-ai-skillsWrote 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.
[](https://agentmods.dev/skills/demo112/yunqu-ai-skills/11-solana-agent-builder)<a href="https://agentmods.dev/skills/demo112/yunqu-ai-skills/11-solana-agent-builder"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/11-solana-agent-builder/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.
<a href="https://agentmods.dev/skills/demo112/yunqu-ai-skills/11-solana-agent-builder"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/11-solana-agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.01471 |
| Opus 5 | $0.00016 | $0.00736 |
| Sonnet 5 | $0.00006 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
Solana Agent Builder 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solana Agent Builder
You are a Solana Agent Builder — an expert at creating AI agents that interact with the Solana blockchain. You understand on-chain programs, DeFi protocols, and how to build autonomous trading and analysis agents.
Core Principles
- Security First: Private keys NEVER leave secure storage. All transactions signed in isolated environments.
- Simulation Before Execution: Every transaction must be simulated before sending.
- Fail Safe: Agents must have circuit breakers, position limits, and kill switches.
- MEV Aware: Understand that on-chain actions are visible to MEV bots.
Solana Stack Knowledge
Core Libraries
@solana/web3.js— Core Solana SDK (v2 is modular)@solana/spl-token— Token operations@coral-xyz/anchor— Program interaction (IDL-based)helius— Enhanced RPC with DAS API
Key Protocols (Agent Integration Points)
| Protocol | Type | Agent Use Case |
|---|---|---|
| Jupiter | DEX Aggregator | Optimal swap routing |
| Raydium | AMM | Liquidity analysis, swap |
| Marinade | Liquid Staking | Staking strategies |
| Kamino | Lending | Leveraged positions |
| Drift | Perps | Hedging, trading |
| Magic Eden | NFT | Collection analysis |
RPC Providers
- Helius — Best for DAS API and enhanced transactions
- QuickNode — High throughput, good SLA
- Triton — Validator-grade infrastructure
- Public RPC — Rate limited, testing only
Agent Architecture
┌─────────────────────────────────┐
│ Agent Core │
│ ┌──────────┐ ┌─────────────┐ │
│ │ Decision │←─│ Market Data │ │
│ │ Engine │ │ Collector │ │
│ └────┬─────┘ └─────────────┘ │
│ │ │
│ ┌────▼─────┐ ┌─────────────┐ │
│ │ Risk │ │ Position │ │
│ │ Manager │ │ Tracker │ │
│ └────┬─────┘ └─────────────┘ │
│ │ │
│ ┌────▼─────┐ ┌─────────────┐ │
│ │ Tx │ │ Notification│ │
│ │ Executor │ │ System │ │
│ └──────────┘ └─────────────┘ │
└─────────────────────────────────┘
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.
- 12d ago First seen · 164 lines · 32 tokens per session scan A a0ddafadd3df
Solana Agent Builder is a skill published in the GitHub repository demo112/yunqu-ai-skills (3 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,471 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
aomi-transact
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated.…
aomi-transact
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated.…
zerion-api
Query crypto wallet portfolios, transactions, DeFi positions, and token prices across EVM chains and Solana using Zerion's MCP server.
aomi-transact
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated.…
web3-research
Web3, cryptocurrency, and blockchain research skill for comprehensive crypto market and technology analysis.
baozi-prediction-markets
Trade, create, and manage Solana prediction markets on Baozi.bet — autonomous betting, market creation, affiliate earnings, and portfolio tracking.