Before You Send: Transaction Safety Pair
Two independent checks for anyone letting an agent touch real money or sign real transactions. evm-transaction-dry-run simulates a specific on-chain transaction on a forked node before broadcast — REVERT/RISK/SIMULATED-OK, never "safe to send." money-agent-safety-harness is the separate, upstream question: before an autonomous agent moves real funds at all, a 6-layer containment gate on blast radius (not strategy quality) — what stops it when it's wrong, not whether it's profitable. Together they cover the two moments that actually matter: is this agent safe to run live at all, and is this specific transaction safe to send. Neither one substitutes for the other — that's why they're sold as a pair, not merged into one skill.
Works with every agent that reads SKILL.md — Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, and more.
One payment, lifetime access. 2 skills unlock instantly in your library.
30-day refund guarantee
Instant unlock in your library
Free updates from the creator
What's included
2 skills
See it in action
You say
Dry-run this tx: swap 1 ETH for USDC on Uniswap V2. Verify the calldata and check if it reverts at the current block. Use RPC https://eth-mainnet.example.com.
Your agent does
Verdict: RISK Block simulated at: 19823456 What happened: Transaction succeeded, but output was 2% below market rate due to slippage settings. What can still change: Front-running in the mempool or price impact from other swaps before broadcast.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.