Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Autonomous Solana token sniper and trading bot. Monitors new token launches on Raydium/Jupiter, evaluates rugpull risk with LLM analysis, auto-buys promising launches, and manages exit strategies. Use when user wants to snipe Solana token launches, trade memecoins, monitor new Solana pairs, or build a Solana trading bot. Supports cron-based monitoring, take-profit/stop-loss, and portfolio tracking.
Autonomous Solana token sniper and trading bot. Monitors new token launches on Raydium/Jupiter, evaluates rugpull risk with LLM analysis, auto-buys promising launches, and manages exit strategies. Use when user wants to snipe Solana token launches, trade memecoins, monitor new Solana pairs, or build a Solana trading bot. Supports cron-based monitoring, take-profit/stop-loss, and portfolio tracking.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Autonomous token sniper for Solana. Monitors Raydium and Jupiter for new liquidity pools, evaluates tokens using LLM-powered rugpull detection, and executes buy/sell orders via Jupiter aggregator.
Solana wallet with SOL for gas + trading capital (USDC or SOL) Anthropic API key (uses Haiku for token evaluation ~$0.001/eval) Helius or QuickNode RPC (free tier works, paid recommended for speed)
python3 {baseDir}/scripts/setup.sh Or manually: pip install solana solders httpx aiohttp python-dotenv
Create .env: SOLANA_PRIVATE_KEY=<base58-private-key> LLM_API_KEY=<anthropic-api-key> RPC_URL=https://api.mainnet-beta.solana.com HELIUS_API_KEY=<optional-for-faster-monitoring> BUY_AMOUNT_SOL=0.1 TAKE_PROFIT=2.0 STOP_LOSS=0.5
cp {baseDir}/scripts/sniper.py /opt/sniper/ python3 /opt/sniper/sniper.py
Pool Monitor β Watches Raydium AMM for new liquidity pool creation events Token Analysis β For each new pool, queries token metadata: Mint authority (revoked = good) Freeze authority (revoked = good) LP burned/locked percentage Top holder concentration Contract verification status LLM Risk Assessment β Sends token data to Claude Haiku for rugpull probability estimate Auto-Buy β If risk score < threshold, buys via Jupiter aggregator for best price Position Management β Monitors positions with take-profit and stop-loss triggers Auto-Sell β Exits via Jupiter when TP/SL hit
Each token gets scored 0-100 (lower = safer): FactorWeightRed FlagMint authority25%Not revokedFreeze authority20%Not revokedLP lock20%< 80% lockedTop 10 holders15%> 50% supplyContract age10%< 1 hourLLM sentiment10%Negative assessment Default buy threshold: risk score < 40
Configurable in .env: BUY_AMOUNT_SOL β Amount per snipe (default: 0.1 SOL) TAKE_PROFIT β Exit multiplier (default: 2.0 = 100% gain) STOP_LOSS β Exit multiplier (default: 0.5 = 50% loss) MAX_POSITIONS β Max concurrent positions (default: 5) MIN_LIQUIDITY β Minimum pool liquidity in USD (default: $5000) SLIPPAGE_BPS β Slippage tolerance in bps (default: 500 = 5%)
Use a DEDICATED wallet with only what you're willing to lose Memecoin trading is extremely high risk β most new tokens go to zero Never use your main wallet's private key Start with tiny amounts (0.01-0.1 SOL per trade) Monitor actively β this is not a set-and-forget system RPC rate limits β Free Solana RPC will miss fast launches. Use Helius/QuickNode for serious sniping.
See references/jupiter-api.md for Jupiter aggregator API docs See references/raydium-pools.md for pool monitoring details
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.