Skip to main content
Routines are deterministic Python functions that agents call for data processing. They reduce token usage and make agent behavior reproducible.

​
Why Routines?

Without routines, agents spend tokens computing indicators every tick. With routines:
  • Session time drops from 2 minutes to under 1 minute
  • Token usage reduced by moving computation to Python
  • Results are reproducible - same input, same output

​
Built-in Routines

Condor includes common routines:
RoutineDescription
technical_analysisEMA, RSI, support/resistance
funding_ratesFetch perpetual funding rates
volume_analysisVolume profile and VWAP

​
Using Routines

Agents call routines via MCP tools: 
Agent: "Let me analyze SOL-USDT..."
→ Calls run_routine("technical_analysis", {pair: "SOL-USDT"})
→ Returns: {trend: "bullish", ema_7: 156.2, support: [154.5, 152.0]...}
Agent: "Trend is bullish with support at $154.50..."

​
Create a Custom Routine

​
1. Create the File

In your agent’s routines/ folder: 
# trading_agents/sol_scalper/routines/momentum_scanner.py

async def scan_momentum(
    connector_name: str = "binance_perpetual",
    trading_pair: str = "SOL-USDT",
    lookback: int = 20
) -> dict:
    """
    Scan for momentum breakouts.

    Args:
        connector_name: Exchange connector
        trading_pair: Market to analyze
        lookback: Number of candles

    Returns:
        Momentum analysis with signal
    """
    from hummingbot_api_client import get_candles

    candles = await get_candles(connector_name, trading_pair, lookback)

    # Calculate momentum
    closes = [c.close for c in candles]
    momentum = (closes[-1] - closes[0]) / closes[0] * 100

    # Volume confirmation
    volumes = [c.volume for c in candles]
    avg_volume = sum(volumes) / len(volumes)
    volume_surge = volumes[-1] > avg_volume * 1.5

    # Generate signal
    if momentum > 2 and volume_surge:
        signal = "strong_bullish"
    elif momentum > 1:
        signal = "bullish"
    elif momentum < -2 and volume_surge:
        signal = "strong_bearish"
    elif momentum < -1:
        signal = "bearish"
    else:
        signal = "neutral"

    return {
        "momentum_pct": round(momentum, 2),
        "volume_surge": volume_surge,
        "signal": signal,
        "price": closes[-1]
    }

​
2. Register the Routine

Add to your agent’s config or the routine will be auto-discovered.

​
3. Use in Agent

Update your agent.md: 
## Entry Rules

1. Run momentum_scanner routine
2. If signal is "strong_bullish" → Open long
3. If signal is "strong_bearish" → Open short
4. Otherwise → Wait

​
4. Test

Run a dry run to verify: 
/agent → SOL Scalper → Dry Run

Dry Run Result:
- Ran momentum_scanner
- Result: {signal: "strong_bullish", momentum: 2.5%}
- Decision: Would open LONG

​
Routine Best Practices

Same input should always produce same output. Avoid randomness or time-based logic.
Return dictionaries with clear field names. The agent will interpret the results.
Return error states rather than raising exceptions:
if not candles:
    return {"error": "No candle data available"}
The agent reads docstrings to understand what the routine does.

​
Global vs Agent-Specific

LocationScope
~/condor/routines/Available to all agents
trading_agents/{slug}/routines/Specific to one agent
Agent-specific routines override global ones with the same name.

​
View Available Routines

You: What routines are available?

Condor: Available routines for SOL Scalper:

Agent-specific:
- momentum_scanner: Scan for momentum breakouts

Global:
- technical_analysis: EMA, RSI, support/resistance
- funding_rates: Fetch perpetual funding rates
- volume_analysis: Volume profile and VWAP

​
What’s Next?

You’ve completed the Getting Started guide! You now know how to:
  • ✓ Install Condor and Hummingbot API
  • ✓ Add exchange credentials
  • ✓ View your portfolio
  • ✓ Build a Trading Agent
  • ✓ Manage agent sessions
  • ✓ Create custom routines

Trading Agents

Deep dive into agent architecture

Executors

Learn about executor types

MCP Tools

Explore all available tools

API Reference

Full API documentation