mev-sandwich

mev-sandwich is a skill for Claude Code from MingyiSecLab/Mingyi-Atlas. It costs 57 tokens per session (1,178 once invoked), scanned A, a copy of contracts-mev-sandwich, Apache-2.0.

A security-audit guide for MEV sandwich attacks, where an attacker places trades before and after another person's decentralised-exchange swap. The first trade changes the price, causing the victim's trade to execute less favourably.

In plain words
What is it for?
Use it to inspect pending swaps, slippage limits, transaction ordering, private transaction routes, and sandwich opportunities on decentralised exchanges.
Why use it?
Loose slippage settings can let attackers profit from a visible pending trade while the person making the swap receives a worse price.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to inspect pending swaps, slippage limits, transaction ordering, private transaction routes, and sandwich opportunities on decentralised exchanges.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/mev-sandwich
Install

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.

Any agent
npx skills add MingyiSecLab/Mingyi-Atlas --skill mev-sandwich
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

Made for: Claude Code.

Wrote 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.

agentmods badge for mev-sandwich

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/mev-sandwich/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/mev-sandwich)
Your own site
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/mev-sandwich"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/mev-sandwich/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.

agentmods 80×15 button for mev-sandwich

Your own site · 80×15
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/mev-sandwich"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/mev-sandwich.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,178 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01178
Opus 5 $0.00028 $0.00589
Sonnet 5 $0.00011 $0.00236
Haiku 4.5 $0.00006 $0.00118

Measured 9d ago against content hash c0916f47ac27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mev-sandwich 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 9d 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.

Origin

This is a copy

98% identical to contracts-mev-sandwich — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/skills/standard/contracts/mev-sandwich/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MEV Sandwich Attack

You observe a victim's DEX swap in the mempool. Sandwich it: buy the same token before the victim (pushing price up), let the victim swap at a worse price, then sell after them.

Detect a sandwichable swap

# Stream pending transactions
from web3 import Web3
w3 = Web3(Web3.HTTPProvider("https://eth.merkle.io"))
# Or: subscribe to alchemy/blocknative streams

# Filter for Uniswap V2 swapExactTokensForTokens or V3 exactInputSingle
# Look at the swap amount + slippage tolerance (deadline + minAmountOut)
# Sandwichable when: swap_amount * slippage > sandwich_gas_cost * 2

Math: profitable when victim's slippage tolerance exceeds your gas cost. Typical threshold for ETH/USDC swaps: victim swap >$10k with >1% slippage.

Construct the sandwich bundle

// Bundle: 3 tx in same block, in order
// 1. attacker_tx_1: swap baseToken -> token (push price UP)
// 2. victim_tx:     swap baseToken -> token (worse price now)
// 3. attacker_tx_2: swap token -> baseToken (sell back at higher price)
// Flashbots bundle (Ethereum mainnet — others have similar private RPCs)
const ethers = require("ethers");
const { FlashbotsBundleProvider } = require("@flashbots/ethers-provider-bundle");

const provider = new ethers.providers.JsonRpcProvider(process.env.RPC);
const wallet = new ethers.Wallet(process.env.PK, provider);
const fb = await FlashbotsBundleProvider.create(provider, wallet, "https://relay.flashbots.net");

const blockNumber = await provider.getBlockNumber();
const bundle = [
  { signer: wallet, transaction: attackerTx1 },  // front-run
  { signedTransaction: rawVictimTx },             // victim from mempool
  { signer: wallet, transaction: attackerTx2 },  // back-run
];

const signedBundle = await fb.signBundle(bundle);
await fb.sendRawBundle(signedBundle, blockNumber + 1);

JIT (Just-In-Time) liquidity sandwich

Uniswap V3 concentrated liquidity lets you provide liquidity in a tight range for one block:

Read the full file on GitHub · 117 lines

Changes

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.

  1. 9d ago First seen · 117 lines · 57 tokens per session scan A c0916f47ac27

Subscribe to this mod's changes

mev-sandwich is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,178 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to contracts-mev-sandwich, differing in 2 lines, and is treated as a copy.