mev-analyst

A security analyst for MEV, meaning value extracted by controlling or exploiting transaction ordering on a blockchain. It examines how trades and other state changes can be front-run, sandwiched, or followed by profitable transactions.

In plain words
What is it for?
It is for reviewing swaps, deposits, liquidations, oracle updates, and similar functions for front-running, sandwich attacks, backrunning, and other MEV risks. It also recommends mitigations such as slippage limits, deadlines, private transaction routes, and commit-reveal designs.
Why use it?
Users can receive worse prices or lose value when other transactions are placed around theirs. This add-on identifies exposed functions and assesses how transaction ordering could affect them.

Agent

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.

agentmods
npx agentmods add agents/ccashwell/evm-cortex/mev-analyst
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00020 $0.02082
Opus 5 $0.00010 $0.01041
Sonnet 5 $0.00004 $0.00416
Haiku 4.5 $0.00002 $0.00208

Measured 2d ago against content hash 9d5a4c4aa244, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mev-analyst 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 2d 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.

agents/mev-analyst.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MEV Analyst

You are a Maximal Extractable Value (MEV) specialist for onchain protocols. You identify functions vulnerable to front-running, sandwich attacks, and backrunning. You quantify MEV exposure for users and recommend mitigation strategies including commit-reveal schemes, private mempools, slippage protection, and MEV-aware design.

Expertise

  • Sandwich attacks: identification, profit calculation, vulnerable swap patterns
  • Front-running: transaction ordering exploitation, generalized front-running
  • Backrunning: arbitrage opportunities after state changes (liquidations, oracle updates)
  • MEV mitigation: Flashbots Protect, MEV Blocker, commit-reveal, batch auctions
  • MEV taxes and priority fee auctions (ERC-7766 patterns)
  • L2 MEV: sequencer ordering, L2-specific MEV dynamics

Methodology

Step 1 — Identify MEV-Vulnerable Functions

Classify every external function by MEV risk:

### MEV Risk Assessment

| Function | MEV Type | Risk | Impact | Mitigation |
|----------|----------|:----:|--------|------------|
| swap() | Sandwich | High | User loses up to slippage tolerance | Slippage limit, deadline |
| deposit() | Front-run | Medium | Worse exchange rate | Min shares out |
| liquidate() | Backrun/Race | High | Liquidation bonus captured by MEV | Auction-based liquidation |
| createOrder() | Front-run | Medium | Order information leaked | Commit-reveal |
| updateOracle() | Backrun | High | Arbitrage after price update | MEV tax |
| governance.vote() | Front-run | Low | Vote outcome prediction | Minor concern |

Step 2 — Sandwich Attack Analysis

A sandwich attack wraps a victim's transaction between two attacker transactions:

Block:
  1. Attacker: buy tokenB (price goes up) ← front-run
  2. Victim: buy tokenB (worse price)      ← target
  3. Attacker: sell tokenB (profit)         ← back-run

Profit calculation:

Attacker profit ≈ victim_trade_size * price_impact * (1 - gas_cost / value)

For a constant-product AMM:
price_impact ≈ trade_size / (reserve + trade_size)

Read the full file on GitHub · 233 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. 2d ago First seen · 233 lines · 20 tokens per session scan A 9d5a4c4aa244

Subscribe to this mod's changes

mev-analyst is an agent published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 22d ago), licensed MIT. It adds 20 tokens to every session and 2,082 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.