Anthropic (Claude)

Anthropic’s Claude models provide advanced reasoning capabilities for security analysis. This guide covers configuration and best practices.

Available Models

Authentication

API Key Setup

1. Get your API key from console.anthropic.com
2. Run the authentication command:

cyberstrike auth login
# Select: Anthropic
# Enter your API key

Environment Variable

export ANTHROPIC_API_KEY="sk-ant-api03-..."

Add to your shell profile for persistence:

echo 'export ANTHROPIC_API_KEY="sk-ant-..."' >> ~/.zshrc

Configuration File

{
  "provider": {
    "anthropic": {
      "options": {
        "apiKey": "{env:ANTHROPIC_API_KEY}"
      }
    }
  }
}

Model Configuration

Set Default Model

{
  "model": "anthropic/claude-sonnet-4-20250514"
}

Command Line Override

cyberstrike --model anthropic/claude-opus-4-5-20251101

In-Session Switching

/model
# Select Claude model

Extended Thinking

Enable extended thinking for complex security analysis:

{
  "provider": {
    "anthropic": {
      "options": {
        "thinking": {
          "type": "enabled",
          "budgetTokens": 10000
        }
      }
    }
  }
}

When to Use Extended Thinking

• Complex vulnerability chains
• Multi-step attack planning
• Code review with deep analysis
• Architecture security review

Token Usage

Monitor Usage

/cost

Displays:

Session Token Usage
━━━━━━━━━━━━━━━━━━━
Input:  45,230 tokens
Output: 12,450 tokens
Cache:  32,100 tokens (read)
Total:  $0.42

Prompt Caching

Anthropic supports prompt caching for repeated context:

{
  "provider": {
    "anthropic": {
      "options": {
        "cacheControl": true
      }
    }
  }
}

Rate Limits

Anthropic applies rate limits based on your tier:

Handling Rate Limits

Cyberstrike automatically handles rate limits with exponential backoff:

{
  "provider": {
    "anthropic": {
      "options": {
        "maxRetries": 3,
        "retryDelay": 1000
      }
    }
  }
}

Best Practices

Model Selection

Cost Optimization

1. Use Haiku for repetitive tasks
2. Enable prompt caching
3. Use /compact for long sessions
4. Limit context with focused prompts

Security

1. Never commit API keys to repositories
2. Use environment variables
3. Rotate keys periodically
4. Monitor usage on Anthropic dashboard

Troubleshooting

Invalid API Key

Error: Invalid API key

Verify your key:

• Starts with sk-ant-api03-
• No trailing whitespace
• Key is active in console

Rate Limit Exceeded

Error: Rate limit exceeded

Solutions:

• Wait and retry
• Upgrade your tier
• Use smaller context

Model Not Available

Error: Model not found

Check model ID is correct and available in your region.

Related Documentation

• Providers Overview - All supported providers
• Configuration - Full configuration options
• Authentication - Setup guide