arbitrage-analysis

arbitrage-analysis is a skill for Claude Code, Codex from 0xendale/evm-agent-toolkit. It costs 64 tokens per session (865 once invoked), scanned A, original, MIT.

An analysis method for finding and measuring DeFi arbitrage opportunities. DeFi means blockchain-based financial services, and arbitrage means seeking price differences between markets.

In plain words
What is it for?
Checking cross-exchange, triangular, and stablecoin price opportunities and producing a net-profit analysis without executing trades.
Why use it?
It accounts for fees, network costs, and price impact, so a visible price spread is not mistaken for actual profit.

Skill for Claude CodeCodex

Part of the evm-agent-toolkit plugin — 3 skills, 1 MCP server shipped together

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 skills/0xendale/evm-agent-toolkit/arbitrage-analysis
Any agent
npx skills add 0xendale/evm-agent-toolkit --skill arbitrage-analysis
Clone the repo
git clone --depth 1 https://github.com/0xendale/evm-agent-toolkit

Made for: Claude Code, Codex.

Or install evm-agent-toolkit, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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 arbitrage-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xendale/evm-agent-toolkit/arbitrage-analysis.svg)](https://agentmods.dev/skills/0xendale/evm-agent-toolkit/arbitrage-analysis)
Your own site
<a href="https://agentmods.dev/skills/0xendale/evm-agent-toolkit/arbitrage-analysis"><img src="https://agentmods.dev/badge/skills/0xendale/evm-agent-toolkit/arbitrage-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 865 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 $0.00064 $0.00865
Opus 5 $0.00032 $0.00432
Sonnet 5 $0.00013 $0.00173
Haiku 4.5 $0.00006 $0.00086

Measured 4d ago against content hash e7c8d228bd32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arbitrage-analysis 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 4d 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.

skills/arbitrage-analysis/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arbitrage Analysis

Overview

Surface and quantify price-dislocation opportunities across venues, net of fees, gas, and slippage. This is an analysis skill: it produces an opportunity ledger, it does not execute trades.

The Iron Rule: never call a route profitable without subtracting fees, gas, AND slippage. A gross spread is not profit. Report the size band where net profit is positive, or say there is none.

When to Use

  • Screening DeFi venues for cross-DEX, triangular, or stablecoin-depeg arbitrage
  • Symptoms: "is there an arb here?", spread/MEV/price-dislocation questions, quantifying an opportunity net of cost

Do NOT use for: security audits (use vulnerability-scanning) or gas optimization (use gas-optimization). Do NOT treat its output as trade authorization.

Workflow

Four reasoning steps, in order.

  1. Seek — From the pool/pair/quote inputs, detect dislocations against the thresholds in reference/strategies.md. List candidates with venues and observed spread.
  2. Innovate — Propose a concrete route per candidate (the leg sequence and venues).
  3. Execute — Compute net_bps = spread_bps - fee_bps - gas_cost_bps - slippage_bps - validator_bribe_bps for the specific trade size. In competitive L1 environments, bribes can consume 90-95% of gross profit. Factor in Maximal Arbitrage Value (MAV) for AMMs. Keep only routes with net_bps > 0; record the viable size band. When an MCP server is available: use evm_simulate_transaction to read live pool quotes, evm_trace_call to dry-run a route leg and read its gas cost from the trace, and evm_decode_calldata to classify competing pending transactions.
  4. Manage — Emit the opportunity ledger: route, gross spread, each cost component, net bps, viable size band, and the reality caveats (MEV, depth, staleness).

Quick Reference

Strategy Min spread (bps) Net rule
Cross-DEX spot 30 spread - fee - gas - slippage > 0
Triangular 45 round-trip net > 0 across 3 legs
Stable depeg 15 net > 0 after fee+gas+slippage

Read the full file on GitHub · 66 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 66 lines · 64 tokens per session scan A e7c8d228bd32

Subscribe to this mod's changes

arbitrage-analysis is a skill published in the GitHub repository 0xendale/evm-agent-toolkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 865 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

ethereum-development

Production-grade Ethereum/EVM development workflow for smart contracts, dApps, transactions, clients, gas optimization, testing, security review, deployment, verification, monitoring, and incident response across Foundry, Hardhat, Solidity, TypeScript, viem, ethers, wagmi, and common EVM networks.

dirtybits/agent-skills · 64 tokens

propfund

Trade on PropFund, the decentralized on-chain prop firm for AI agents. Use this skill to get funded with the liquidity pool's capital and trade without risking your own bankroll — pass a transparent evaluation, then place leveraged long/short trades with mandatory stop-loss/take-profit and on-chain risk limits, and…

NO7r34L/PropFund.eth · 103 tokens

openocean

OpenOcean DEX aggregator: quote and execute swaps with balance-delta verification. Use when comparing routes or executing a swap via OpenOcean (e.g. quote DAI→USDC, swap with slippage check, verify post-trade balance).

Starchild-ai-agent/official-skills · 54 tokens

sign-swap

Sign a swap transaction through the Agentic Vault MCP server.

agenticvault/agentic-vault · 0 tokens

aomi-transact

Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated.…

aomi-labs/skills · 221 tokens

Gas Optimizer

Advanced gas optimization tool for Ethereum and EVM-compatible chains. Analyzes transactions, simulates gas usage, suggests optimal gas prices, batches transactions, and implements gas-saving patterns for smart contract interactions.

XSpoonAi/spoon-awesome-skill · 44 tokens