agentleFS
Sign inStart free
weininghuiweininghui/skills/btc15-autonomous-market/SKILL.md

btc15-autonomous-market

Skill1 starsChanged 14 days agoMITView on GitHub

BTC15 Autonomous Prediction Market A fully autonomous BTC prediction market powered by three cooperating agents using USDC.

  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No human interaction is required once the system starts.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

btc15-autonomous-market

BTC15 Autonomous Prediction Market A fully autonomous BTC prediction market powered by three cooperating agents using USDC.

The Problem Most prediction markets require human intervention for liquidity, trading, or resolution. This limits scalability and prevents true agent-native economic systems.

This skill demonstrates a fully autonomous prediction market loop where agents:

provide liquidity, trade based on market data, resolve outcomes, and settle value onchain in USDC.

No human interaction is required once the system starts.

Agents This system consists of three autonomous agents:

Maker Agent Continuously provides liquidity by minting YES/NO shares and posting sell offers.

Trader Agent Monitors BTC price movement and places directional bets based on predefined thresholds.

Resolver Agent Fetches BTC price data at round start and end, resolves the market outcome, and redeems winnings automatically.

Economic Loop Each round follows a fully autonomous lifecycle:

  1. Maker provides liquidity in USDC.
  2. Trader observes BTC movement and places a bet.
  3. Round ends.
  4. Resolver determines outcome using external price data.
  5. Contract resolves onchain.
  6. Winnings are redeemed automatically.
  7. Capital is reused in the next round.

This creates a continuous onchain economic loop:

liquidity → trading → resolution → settlement → reinvestment

Key Properties Fully autonomous: no human steps required after launch. USDC settlement: stable unit of account for agent commerce. Continuous operation: agents run indefinitely. Onchain resolution and redemption.

Installation Clone the main project:

git clone https://github.com/kamal-sutra/clawbtc15.git cd clawbtc15

Install Python dependencies:

pip install web3 python-dotenv requests

Create environment file:

cp .env.example .env

Fill in the following values:

RPC=https://sepolia.base.org

MARKET=0x03956BC8745618eCCD7670073f7cAa717caDC5F4 USDC=0x036cbd53842c5426634e7929541ec2318f3dcf7e

MAKER_KEY=<your maker private key> TRADER_KEY=<your trader private key> RESOLVER_KEY=<your resolver private key>

Commands Run maker:

run-maker

Run trader:

run-trader

Run resolver:

run-resolver

Run all agents:

run-all

Contract Details Network: Base Sepolia USDC: 0x036cbd53842c5426634e7929541ec2318f3dcf7e Market: 0x03956BC8745618eCCD7670073f7cAa717caDC5F4

Use Cases Agent-native trading systems. Autonomous market making. Onchain economic coordination between agents. Continuous prediction markets.

Built for the USDC Hackathon (Feb 2026).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free