Mev logo

Mev

CommunityPopular
alsk1992
mev

MEV protection against sandwich attacks and front-running

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill namemev
Stars
2.8K
Forks
336
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by alsk1992 on GitHub. Read the source before you install it.

Installation

Install the Mev AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alsk1992/CloddsBot.git /tmp/CloddsBot
mkdir -p .claude/skills
cp -r /tmp/CloddsBot/src/skills/bundled/mev .claude/skills/mev
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mev in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mev on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mev is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MEV Protection - Complete API Reference

Protect trades from MEV (Maximal Extractable Value) attacks including sandwich attacks and front-running.


Chat Commands

Protection Settings

/mev                                Show current protection
/mev status                         Protection status
/mev enable                         Enable protection
/mev disable                        Disable protection

Configure Protection

/mev level aggressive               Maximum protection
/mev level standard                 Balanced protection
/mev level minimal                  Basic protection
/mev provider flashbots             Use Flashbots
/mev provider mev-blocker           Use MEV Blocker

Check Transaction

/mev check <tx-hash>                Check if tx was attacked
/mev simulate <order>               Simulate MEV risk

TypeScript API Reference

Create MEV Protection

typescript
import { createMEVProtection } from 'clodds/mev';

const mev = createMEVProtection({
  // Default level
  level: 'standard',

  // Providers
  providers: {
    ethereum: 'flashbots',    // 'flashbots' | 'mev-blocker'
    solana: 'jito',           // 'jito' | 'standard'
  },

  // Settings
  maxPriorityFee: 5,  // gwei
  bundleTimeout: 60,  // seconds
});

Execute Protected Trade

typescript
// EVM trade with protection
const result = await mev.executeProtected({
  chain: 'ethereum',
  type: 'swap',
  tokenIn: 'USDC',
  tokenOut: 'ETH',
  amountIn: 10000,
  minAmountOut: calculateMinOut(10000, 0.5),  // 0.5% slippage
});

console.log(`Tx hash: ${result.txHash}`);
console.log(`Protected: ${result.protected}`);
console.log(`Bundle ID: ${result.bundleId}`);
console.log(`Savings: $${result.estimatedSavings}`);

Flashbots (Ethereum)

typescript
// Submit via Flashbots Protect
const result = await mev.flashbots({
  to: routerAddress,
  data: swapCalldata,
  value: 0,
  maxFeePerGas: parseGwei('50'),
  maxPriorityFeePerGas: parseGwei('2'),
});

console.log(`Submitted to Flashbots`);
console.log(`Bundle hash: ${result.bundleHash}`);

// Wait for inclusion
const status = await mev.waitForInclusion(result.bundleHash);
console.log(`Included in block: ${status.blockNumber}`);

MEV Blocker (Ethereum)

typescript
// Use MEV Blocker by CoW Protocol
const result = await mev.mevBlocker({
  to: routerAddress,
  data: swapCalldata,
  value: 0,
});

// MEV Blocker automatically:
// - Protects from sandwich attacks
// - Backruns profitable MEV to you
// - Returns any captured MEV
console.log(`MEV captured: $${result.mevCaptured}`);

Jito (Solana)

typescript
// Submit via Jito bundles
const result = await mev.jito({
  instructions: swapInstructions,
  tip: 10000,  // lamports tip to validators
});

console.log(`Bundle ID: ${result.bundleId}`);
console.log(`Status: ${result.status}`);

Check Transaction

typescript
// Check if a past transaction was attacked
const analysis = await mev.analyzeTransaction(txHash);

console.log(`Was attacked: ${analysis.wasAttacked}`);
if (analysis.wasAttacked) {
  console.log(`Attack type: ${analysis.attackType}`);
  console.log(`Attacker: ${analysis.attacker}`);
  console.log(`Loss: $${analysis.estimatedLoss}`);
  console.log(`Frontrun tx: ${analysis.frontrunTx}`);
  console.log(`Backrun tx: ${analysis.backrunTx}`);
}

Simulate MEV Risk

typescript
// Before trading, check MEV risk
const risk = await mev.simulateRisk({
  chain: 'ethereum',
  type: 'swap',
  tokenIn: 'USDC',
  tokenOut: 'PEPE',
  amountIn: 50000,
});

console.log(`MEV risk: ${risk.level}`);  // 'low' | 'medium' | 'high'
console.log(`Estimated max loss: $${risk.maxLoss}`);
console.log(`Recommendation: ${risk.recommendation}`);

if (risk.level === 'high') {
  console.log('⚠️ High MEV risk - use protection!');
}

Protection Levels

typescript
// Aggressive - maximum protection, slower
mev.setLevel('aggressive', {
  usePrivateMempool: true,
  bundleOnly: true,
  maxSlippage: 0.1,
  waitForProtection: true,
});

// Standard - balanced protection
mev.setLevel('standard', {
  usePrivateMempool: true,
  bundleOnly: false,
  maxSlippage: 0.5,
});

// Minimal - basic protection
mev.setLevel('minimal', {
  usePrivateMempool: false,
  bundleOnly: false,
  maxSlippage: 1.0,
});

MEV Attack Types

AttackDescriptionProtection
SandwichFront + backrun your tradePrivate mempool
Front-runningCopy your trade firstPrivate mempool
Back-runningProfit after your tradeJito/Flashbots
JIT LiquidityManipulate poolSlippage limits

Protection Providers

ChainProviderMethod
EthereumFlashbots ProtectPrivate relay
EthereumMEV BlockerCoW Protocol
SolanaJitoBundle submission
L2sNativeSequencer protection

When to Use Protection

Trade SizeTokenRecommendation
< $1,000MajorMinimal
$1,000 - $10,000MajorStandard
> $10,000MajorAggressive
Any sizeMeme/Low liquidityAggressive

Best Practices

  1. Always protect large trades — MEV bots watch everything
  2. Use tight slippage — Limits attack profitability
  3. Check before trading — Simulate MEV risk
  4. Review transactions — Learn from past attacks
  5. L2s are safer — Sequencer provides natural protection

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mev AI skill do?

MEV protection against sandwich attacks and front-running

Why use Mev on TypingMind?

Because you install it once and use it with any model. Mev is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mev in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/mev. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mev?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mev?

As many as you like. As long as a model supports skills, you can use Mev with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mev AI skill free?

Yes. It is published on GitHub by alsk1992 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇