CloddsBot's README has a one-liner that explains everything: Claude + Odds = Clodds. The name captures the project's essence—Claude as the brain, odds markets as the battlefield, packaged as a conversational trading terminal.
12 days of development. 10.7k clones in 14 days. 377 stars in a single day. It was rushed together for the Colosseum Agent Hackathon (a Solana hackathon), but the polish doesn't look like a 12-day build.
21 Chat Platforms × 10 Prediction Markets × 7 Futures Exchanges
CloddsBot's coverage is frankly absurd:
- Messaging channels: 21 platforms including Telegram, Discord, WhatsApp, Slack, Teams, Signal, Matrix, iMessage, LINE, and Nostr, plus a built-in WebChat
- Prediction markets: Polymarket, Kalshi, Betfair, Smarkets, Drift, Manifold, Metaculus, PredictIt, Opinion.xyz, Predict.fun
- Perpetual futures: Binance, Bybit, Hyperliquid, MEXC, Drift, Percolator, Lighter—with up to 200x leverage
- On-chain: the full Solana stack (Jupiter, Pump.fun, Raydium, Orca, Bags.fm) plus five EVM chains (Base, Ethereum, Arbitrum, Optimism, Polygon) via Uniswap V3, 1inch, and Virtuals Protocol
- Bittensor subnet mining: TAO
- Momentum strategies, mean reversion, penny clipper, expiry fade
- DCA bots, smart routing, whale tracking, copy trading
- Arbitrage detection, cross-market hedging
- Round-based strategies (5min, 15min, 1h, 4h, daily) for Polymarket's BTC/ETH/SOL/XRP binary markets
- Circuit breakers: automatic halt when daily loss limits trigger
- VaR/CVaR: value-at-risk and conditional VaR to quantify tail risk
- Volatility regime detection: separating normal from abnormal volatility
- Stress testing: replaying historical extreme scenarios
- Kelly sizing: mathematically grounded position sizing based on win rate and odds
- Kill switch: one-click close of all positions
- Honeypot detection (buy in, can't sell out)
- Rug pull analysis (withdrawable liquidity)
- Holder concentration (whales can dump)
- Risk scoring
This isn't a trading bot—it's a trading operating system. You send commands from any chat platform, Claude parses the intent, invokes one or more of 121 skills, and executes the trade.
121 Skills: Trading Strategies as Composable Blocks
The most interesting design decision is the skill system. 121 built-in skills, each a standalone unit of trading capability:
The design mirrors Claude Code's skill system—not one monolithic agent, but many small, focused skills that the agent invokes on demand. The benefits are composability, extensibility, and independent testability.
But CloddsBot's skills aren't written for developers—they're written for trading strategies themselves. Each skill encapsulates a complete trading logic (entry conditions, exit conditions, position management, risk control). Claude's job is to understand user intent, pick the right skill, and pass the right parameters.
The Risk Engine: Not Optional, Core
The biggest risk with a trading agent isn't losing money—it's losing money without knowing. CloddsBot's risk engine handles:
In a traditional quant firm, this is an entire risk department's job. CloddsBot compresses it into one open-source project anyone can run.
Token Safety: Rug Pull Protection
On-chain trading carries a risk that doesn't exist in traditional finance—the token itself may be a scam. CloddsBot integrates GoPlus for on-chain token audits:
MCP Server Mode: Trading Directly from Claude Desktop
CloddsBot can run as an MCP server—clodds mcp install configures Claude Desktop / Claude Code in one step. That means you can say "buy BTC up on Polymarket" in Claude Desktop, and Claude calls CloddsBot's MCP tools to place the trade.
This is the MCP protocol landing in finance. MCP isn't just for letting Claude read files or query databases—it can let Claude place orders for you. Of course, that also means if your Claude gets phished, your money goes with it.
What 12 Days Can Build
CloddsBot was built for a Solana hackathon in 12 days. But the author clearly didn't start from zero—121 skills, 21 messaging channels, 10 prediction markets. That integration effort far exceeds 12 days. The more plausible explanation: the author was already building trading bots, and the hackathon was just the occasion to assemble existing components into an open-source product.
That also explains the 377 stars in a day—this isn't a demo, it's a usable, production-grade tool.
What's Worth Watching
CloddsBot isn't the first trading bot, but it gets several things right:
1. A skill system instead of a monolithic agent—121 independent, composable, extensible skills, isomorphic to Claude Code 2. Chat as trading—pick any of 21 platforms, lowering the barrier to entry 3. Risk engine as core, not add-on—VaR/CVaR/Kelly/circuit breakers, quant-grade risk control 4. MCP server mode—direct trading from Claude Desktop; MCP landing in finance 5. Token safety audits—"due diligence automation" for on-chain trading
The risk is equally obvious: the biggest risk of a Claude-driven trading agent is Claude itself. If a prompt injection attack makes Claude do something unintended, or Claude's reasoning fails under extreme market conditions, the losses are real money. CloddsBot's risk engine targets market risk, not AI safety risk.
But as an open-source project, it proves one thing: the combination of MCP + a skill system is enough to build a trading terminal covering 1000+ markets. The scalability of this architecture goes far beyond what traditional trading bots imagined.
---
GitHub: https://github.com/alsk1992/CloddsBot