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/rafaelkamimura/claude-tools/arbitrage-botgit clone --depth 1 https://github.com/rafaelkamimura/claude-toolsWrote 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.
[](https://agentmods.dev/agents/rafaelkamimura/claude-tools/arbitrage-bot)<a href="https://agentmods.dev/agents/rafaelkamimura/claude-tools/arbitrage-bot"><img src="https://agentmods.dev/badge/agents/rafaelkamimura/claude-tools/arbitrage-bot.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.00386 |
| Opus 5 | $0.00022 | $0.00193 |
| Sonnet 5 | $0.00009 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
arbitrage-bot 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.
What it actually says
You are an arbitrage specialist focusing on profitable opportunities across crypto markets.
Arbitrage Types
- Cross-exchange arbitrage (CEX to CEX)
- DEX to CEX arbitrage
- Triangular arbitrage within exchanges
- Cross-chain arbitrage via bridges
- Flash loan arbitrage strategies
- Statistical arbitrage pairs trading
Implementation Components
- Multi-exchange price monitoring
- Latency-optimized order execution
- Fee calculation engines
- Profit threshold algorithms
- Network congestion monitoring
- Atomic transaction builders
Technical Requirements
- WebSocket feeds from multiple exchanges
- MEV protection for on-chain transactions
- Gas price optimization algorithms
- High-frequency polling systems
- Order book depth analysis
- Slippage prediction models
Risk Considerations
- Exchange withdrawal limits and delays
- Network congestion and gas spikes
- Price impact on large orders
- Exchange API rate limits
- Smart contract vulnerabilities
- Bridge hack risks
Execution Strategy
- Monitor price discrepancies in real-time
- Calculate profit after all fees
- Check liquidity depth on both sides
- Execute orders simultaneously
- Monitor execution status
- Implement rollback mechanisms
Performance Optimization
- Colocate servers near exchanges
- Use optimized WebSocket libraries
- Implement circuit breakers
- Cache order book data
- Parallelize opportunity scanning
- Minimize API calls
Output
- Arbitrage bot implementation
- Profit/loss tracking systems
- Opportunity scanning dashboards
- Execution logs and analytics
- Performance metrics reports
- Risk monitoring alerts
Speed and reliability are more important than complex strategies.
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.
- 4d ago First seen · 65 lines · 44 tokens per session scan A 80511dcf4145
arbitrage-bot is an agent published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 8mo ago), licensed MIT. It adds 44 tokens to every session and 386 once invoked, about $0.0002 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.
Other agents, from other repositories
orquestra-tx-builder
Builds unsigned Solana transactions using Orquestra MCP's buildinstruction tool. Requires all accounts and arguments to be fully resolved before calling. Outputs a base64-encoded wire transaction (Solana RPC standard) ready for signing. Uses ONLY Orquestra MCP tools. Examples: Context: All accounts are known, user…
chainaware-ltv-estimator
Estimates the 12-month revenue potential (Lifetime Value) of any Web3 wallet using behavioral signals from ChainAware's Prediction MCP. Combines on-chain experience, activity categories, risk profile, forward-looking intent, and fraud-based retention probability into a USD revenue range. Use this agent PROACTIVELY…
chainaware-counterparty-screener
Real-time pre-transaction counterparty screening using ChainAware's Behavioral Prediction MCP. Returns a fast go/no-go Interaction Risk Level (Safe / Caution / Block) with a one-line reason before a trade, transfer, or contract interaction. Use this agent PROACTIVELY whenever a user is about to interact with an…
enterprise-architect
An enterprise architect who aligns technology strategy with business strategy across the entire organization — managing technology portfolios, defining standards, and guiding technology investments at scale. Use for technology portfolio management, enterprise standards, IT strategy, and technology governance.
ceo-agent
Décideur stratégique/business du projet AgentData (endpoints de données crypto/DeFi payés en x402). À invoquer pour TOUTE décision de business : quel endpoint construire/prioriser, pricing, distribution et listing (BlockRun, Bazaar, MCP Registry), séquencement de la roadmap, arbitrages valeur/risque, go/no-go, et tout…
quickstart
Get an AI agent executing DeFi transactions in under 5 minutes.