Initialize Claude Agent with Custom Tools

Prompt detail, context, and execution controls for real reuse instead of one-off copying.

implementationReal-time Crypto Fraud Alert Agent with Claude Agents SDKPublic prompt

Operator-ready prompt for reuse, tuning, and workspace runs.

This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.

Best for

Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.

Reuse pattern

Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.

Before first run

Swap domain facts, examples, and any hard-coded entities for your own context.

Tighten the evidence or verification requirement if this is headed toward production.

Decide which failure mode you want to evaluate first before you branch the prompt.

Operator lens

This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.

Best practice: keep one pristine source version, then branch variants around evaluation criteria, evidence thresholds, and output format.
Inspect linked challenge context
Run Profile

Open this prompt inside Workspace when you want a live iteration loop.

Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.

Structured source with 32 active lines to adapt.

Already linked to a challenge workflow.

Sign in to keep private prompt variations.

View linked challenge

Prompt content

Original prompt text with formatting preserved for inspection and clean copy.

Source prompt
32 active lines
7 sections
No variables
1 code block
Raw prompt
Formatting preserved for direct reuse
Start by setting up your development environment for the Claude Agents SDK. Define a `Tool` for fetching simulated crypto transaction data (`get_transaction_details(tx_id: str)`) and another for fetching relevant news articles (`search_crypto_news(query: str)`). Implement basic Python functions that return dummy data for these tools. Then, initialize a Claude agent with these tools, instructing it to monitor for large, suspicious transactions followed by news of scams. Include Python code snippets.

```python
from anthropic import Anthropic
from anthropic.agents import Tool, Agent
import json
import time

# Initialize Anthropic client
client = Anthropic(api_key="YOUR_ANTHROPIC_API_KEY")

# Define a dummy tool for fetching transaction data
def get_transaction_details(tx_id: str) -> str:
    """Fetches details for a given crypto transaction ID."""
    # Simulate fetching data
    if tx_id == "tx3":
        return json.dumps({
            "tx_id": tx_id, "from_addr": "C", "to_addr": "Monero_Mixer", 
            "amount": "1200XMR", "currency": "XMR", "timestamp": "T3"
        })
    return json.dumps({"tx_id": tx_id, "status": "not_found"})

# Define a dummy tool for searching crypto news
def search_crypto_news(query: str) -> str:
    """Searches for crypto news articles related to the query."""
    # Simulate news search
    if "scam" in query.lower() and "whale" in query.lower():
        return json.dumps([{"headline": "Whale loses millions in hardware wallet scam", "content": "A prominent crypto whale reported losing over $282M in BTC and LTC...", "timestamp": "T2.5"}])
    return json.dumps([])

# Create Tool instances
transaction_tool = Tool(name="get_transaction_details", description=get_transaction_details.__doc__, input_schema={"$schema": "http://json-schema.org/draft-07/schema#", "type": "object", "properties": {"tx_id": {"type": "string"}}, "required": ["tx_id"]})
news_tool = Tool(name="search_crypto_news", description=search_crypto_news.__doc__, input_schema={"$schema": "http://json-schema.org/draft-07/schema#", "type": "object", "properties": {"query": {"type": "string"}}, "required": ["query"]})

# Initialize the agent. Your task is to define the agent's prompt and make it use these tools.
# agent = Agent(client=client, tools=[transaction_tool, news_tool], ...)
# response = agent.run("Monitor for suspicious crypto activities and alert on potential scams.")
```

Adaptation plan

Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.

Safe workflow

Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.

Prompt diagnostics

Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.

Sections
7
Variables
0
Lists
0
Code blocks
1
Reuse posture

This prompt already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.

Linked challenge

Real-time Crypto Fraud Alert Agent with Claude Agents SDK

Develop a sophisticated, real-time agent to detect and alert on suspicious cryptocurrency transactions and social engineering scams, inspired by recent crypto fraud incidents. This agent will leverage the Claude Agents SDK to orchestrate complex reasoning, interact with external tools (simulated crypto APIs, news feeds), and perform pattern recognition to identify potential fraud or money laundering activities, such as sudden large conversions to privacy coins like Monero. The system requires an agent capable of continuously monitoring multiple data streams, applying domain-specific knowledge to interpret transaction anomalies, and generating immediate, actionable alerts. It will use Claude 4.5 Sonnet's advanced tool use capabilities and benefit from 'Across AI' for maintaining a persistent memory of known scam patterns and suspicious addresses, ensuring that the agent can learn and adapt over time.

Agent Building
advanced
Prompt origin
Why open it

Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.

Open challenge context