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.
npx agentmods add agents/ccashwell/evm-cortex/mev-analystgit clone --depth 1 https://github.com/ccashwell/evm-cortexWhat 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.
| Model | Per session | Once 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 |
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.
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)
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.
- 2d ago First seen · 233 lines · 20 tokens per session scan A 9d5a4c4aa244
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.