Trench is a high-performance execution skill for AI agents to trade Solana meme coins with MEV protection and automated rug detection.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install trench
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install trench using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Trench?
Trench is a specialized execution framework designed for AI agents operating on the Solana blockchain. By integrating with Openclaw Skills, developers can empower their agents to execute lightning-fast trades, monitor new pool launches on Raydium or Pump.fun, and manage high-volatility positions with precision. It bridges the gap between AI-driven market analysis and low-latency transaction execution.
The skill prioritizes safety and efficiency by incorporating rug detection via Rugcheck API and MEV protection using Jito bundles. Whether you are building an autonomous trading bot or a portfolio assistant, Trench provides the necessary tools within the Openclaw Skills ecosystem to navigate the meme coin landscape safely and profitably.
Trench Use Cases
- Sniping new token launches on Raydium and Pump.fun immediately as liquidity is added.
- Executing rapid buy and sell orders via Jupiter aggregator for optimal price routing.
- Protecting transactions from sandwich attacks and front-running using Jito MEV bundles.
- Automating position management with take-profit, stop-loss, and trailing stop orders.
- Conducting real-time safety audits on token contracts to detect honeypots or liquidity locks.
How Trench Works
- The AI agent identifies a trading opportunity or receives a command to monitor a specific token address.
- Trench utilizes the safety module to perform a rug check and verify token security metrics against the Rugcheck API.
- Upon verification, the execution script calculates the optimal route via the Jupiter V6 API or Raydium pools.
- The transaction is wrapped in a Jito bundle with an optimized priority fee to ensure fast, protected landing on-chain.
- Once confirmed, the position management module tracks PnL and executes exit strategies based on predefined user triggers.
Trench Setup
To integrate Trench with your AI agent, ensure you have your Solana wallet private key and a high-performance RPC endpoint configured.
# Clone the skill repository
git clone https://github.com/openclaw/trench.git
# Install required Python dependencies for Solana interaction
pip install solana anchorpy base58 requests
# Configure your environment variables
export SOLANA_RPC_URL="your_rpc_endpoint"
export PRIVATE_KEY="your_wallet_private_key"
export JITO_BLOCK_ENGINE_URL="https://mainnet.block-engine.jito.wtf"
Trench Data Schema & Taxonomy
Trench maintains a structured approach to trading data and position tracking to ensure Openclaw Skills can report status accurately.
| Module | Purpose | Key Data Points |
|---|---|---|
buy.py / sell.py |
Trade Execution | Slippage, Priority Fees, Jito Tip, Tx Signature |
safety.py |
Risk Assessment | Liquidity Lock, Mint Authority, Top Holder Distribution |
portfolio.py |
Position Tracking | Entry Price, Token Balance, Unrealized PnL, ROI |
monitor.py |
Market Alerts | New Pair Address, Initial Liquidity, Pump.fun Graduation Status |
Trench Advanced Features
- Jito Bundle Integration: Submit transactions directly to block engines to bypass the public mempool and avoid predatory MEV.
- Multi-Wallet Support: Manage and execute trades across a fleet of Solana wallets for complex distribution strategies.
- Real-Time Price Feeds: Integration with DexScreener and Birdeye APIs for sub-second price updates and chart data.
- Automated Trailing Stops: Dynamic exit strategies that adjust the stop-loss level as the token price increases.
- Rug Detection Hooks: Built-in safety checks that can automatically abort trades if malicious contract attributes are detected within the Openclaw Skills workflow.
SKILL.md
Loading
Related Openclaw Skills
Auto Memory Curation
A silent intelligence layer that analyzes every interaction to build a structured, long-term memory of project facts and user preferences.
X Media Parser
A high-performance utility for extracting direct media download links and metadata from X (Twitter) posts without requiring authentication.
SkillsMP Search
A powerful search tool to discover and integrate AI Agent capabilities from the SkillsMP marketplace.
Aria2 Download Skill
A robust Aria2 RPC integration for adding, managing, and monitoring high-speed download tasks from your AI agent environment.
Autotask MCP for Kaseya PSA
A local Docker-based Model Context Protocol (MCP) server to bridge AI agents with Datto/Kaseya Autotask PSA for ticket and project management.
Employee Skills Importer
Automate the transformation of complex employee skill CSV files into clean, idempotent SQL scripts for Supabase.
Featured*
