Overview Claude Code by Anthropic is one of the most powerful AI coding assistants available. Known for exceptional reasoning, clear explanations, and robust code generation.
Claude 3.5 Sonnet (released Oct 2024) is currently the best all-around model for coding tasks.
Quick Start
Get API Key
Go to console.anthropic.com
Sign up or log in
Navigate to API Keys
Click Create Key
Copy your API key (starts with sk-ant-)
Configure Forge
Edit .forge/config.json: { "llms" : { "claude" : { "apiKey" : "sk-ant-api03-..." , "model" : "claude-3-5-sonnet-20241022" } } }
Test Connection
forge task create \ --title "Test Claude" \ --description "Print 'Hello from Claude!'" \ --llm claude Available Models Claude 3.5 Family (Recommended) claude-3-5-sonnet-20241022
Best all-around model for coding
Context: 200K tokens
Speed: Fast
Cost: 3 / M T o k i n p u t , 3/MTok input, 3/ MT o kin p u t ,
Best for: Most coding tasks
{ "llms" : { "claude" : { "model" : "claude-3-5-sonnet-20241022" } } } claude-3-5-haiku-20241022
Fastest and most cost-effective
Context: 200K tokens
Speed: Very fast (3x faster than Sonnet)
Cost: 0.25 / M T o k i n p u t , 0.25/MTok input, 0.25/ MT o kin p u t ,
Best for: Simple tasks, quick fixes
{ "llms" : { "claude-haiku" : { "apiKey" : "sk-ant-..." , "model" : "claude-3-5-haiku-20241022" } } } Claude 3 Family (Legacy) Most powerful, most expensive
Context: 200K tokens
Speed: Slower
Cost: 15 / M T o k i n p u t , 15/MTok input, 15/ MT o kin p u t ,
Best for: Critical architecture decisions
Opus is 5x more expensive than Sonnet. Use sparingly!
Model Comparison
Model Speed Quality Cost Best For 3.5 Sonnet ⭐⭐⭐⭐ ⭐⭐⭐⭐⭐ $$$ Most tasks (recommended) 3.5 Haiku ⭐⭐⭐⭐⭐ ⭐⭐⭐⭐ $ Quick iterations 3 Opus ⭐⭐⭐ ⭐⭐⭐⭐⭐ $$$$$ Critical work only
Configuration Options Basic Configuration { "llms" : { "claude" : { "apiKey" : "sk-ant-api03-..." , "model" : "claude-3-5-sonnet-20241022" } } } Advanced Configuration { "llms" : { "claude" : { "apiKey" : "sk-ant-api03-..." , "model" : "claude-3-5-sonnet-20241022" , "maxTokens" : 8192 , "temperature" : 0.7 , "timeout" : 60000 , "retries" : 3 , "baseUrl" : "https://api.anthropic.com" } } } Maximum tokens in response
Min: 1
Max: 8192
Higher = longer responses, more cost
Randomness of responses (0-1)
0 = Deterministic, consistent
1 = Creative, varied
0.7 = Good balance
Request timeout in milliseconds
Number of retry attempts on failure
Claude’s Strengths Complex Reasoning Claude excels at multi-step logic:
forge task create \ --title "Design authentication system" \ --description " Design a complete auth system with: - JWT token management - Refresh token rotation - Role-based access control - Session management - Password reset flow Consider security, scalability, and maintainability. " \ --llm claude Claude will:
Break down the problem systematically
Consider edge cases
Suggest architectural patterns
Explain trade-offs
Code Refactoring Claude maintains code coherence during refactoring:
forge task create \ --title "Refactor user service to clean architecture" \ --description " Current: Monolithic UserService with 800 lines Goal: Clean architecture with: - Separate domain, application, infrastructure layers - Dependency injection - Unit testable components Preserve all existing functionality. " \ --llm claude Security-Aware Claude considers security implications:
forge task create \ --title "Add file upload endpoint" \ --description " Allow users to upload profile pictures " \ --llm claude Claude will add:
File type validation
Size limits
Malware scanning considerations
Secure file storage
Path traversal protection
Claude’s Weaknesses Can Be Verbose Claude sometimes over-explains:
Solution : Use concise prompts:forge task create \ --title "Add validation" \ --description "Add email validation. Keep it simple." \ --llm claude May Over-Engineer For simple tasks, Claude might create complex solutions:
Solution : Use Haiku for simple tasks:forge task create \ --title "Add console.log for debugging" \ --llm claude-haiku Pricing & Cost Management Current Pricing (as of Oct 2024)
Model Input Output Example Cost 3.5 Sonnet $3/MTok $15/MTok 10K context + 2K response = $0.06 3.5 Haiku $0.25/MTok $1.25/MTok 10K context + 2K response = $0.005 3 Opus $15/MTok $75/MTok 10K context + 2K response = $0.30
Cost Optimization Use Haiku First
Reduce Context
Lower Max Tokens
Monitor Spending
# Start with Haiku forge task create "Add button" --llm claude-haiku # If not good enough, try Sonnet forge task fork 1 --llm claude Saves money on simple tasks Best Practices Task Descriptions Claude responds well to structured descriptions:
Good ✅:forge task create \ --title "Add caching" \ --description " # Goal Add Redis caching to product API # Requirements - Cache GET /api/products for 5 minutes - Invalidate on POST/PUT/DELETE - Handle Redis connection errors gracefully # Constraints - Don't cache user-specific data - Keep existing API contract unchanged " \ --llm claude Bad ❌:forge task create \ --title "make it faster" \ --description "add cache or something" \ --llm claude Using Multiple Claude Models # Quick exploration with Haiku forge task create "Add dark mode" --llm claude-haiku # Refined implementation with Sonnet forge task fork 1 --llm claude # Critical review with Opus forge task fork 1 --llm claude-opus Integration with Forge MCP Support Claude Code works seamlessly with Forge’s MCP server:
// In Claude Code settings { "mcpServers" : { "automagik-forge" : { "command" : "npx" , "args" : [ "automagik-forge" , "--mcp" ], "env" : { "PROJECT_ID" : "your-project-id" } } } } Now you can:
You: "Create a task to add user authentication" Claude Code: [Uses MCP to create task in Forge] Specialized Profiles Create Claude variants for specific tasks:
{ "llms" : { "claude" : { "model" : "claude-3-5-sonnet-20241022" }, "claude-security" : { "model" : "claude-3-5-sonnet-20241022" , "systemPrompt" : "You are a security expert. Always consider security implications..." }, "claude-tester" : { "model" : "claude-3-5-sonnet-20241022" , "systemPrompt" : "You are a testing expert. Write comprehensive tests..." } } } Troubleshooting
Error : “Invalid API key”Solutions :
Verify API key is correct (starts with sk-ant-api03-)
Check for extra spaces or quotes
Ensure key hasn’t been rotated
Generate new key from console.anthropic.com
Error : “Rate limit exceeded”Solutions :
Wait a few minutes
Reduce concurrent tasks
Upgrade Anthropic plan for higher limits
Use exponential backoff:
{ "llms" : { "claude" : { "retries" : 5 , "retryDelay" : 1000 } } }
Issue : Claude taking too longSolutions :
Use Haiku instead of Sonnet
Reduce maxTokens
Simplify task description
Check network latency
Error : “Prompt is too long”Solutions :
Reduce context sent to Claude
Don’t include entire codebase
Use --files to limit scope
Split into smaller tasks
Issue : Different results each timeNormal behavior! AI is non-deterministic.For consistency :{ "llms" : { "claude" : { "temperature" : 0 } } } Rate Limits Anthropic API Limits
Tier RPM TPM TPD Free 5 10K 100K Build (Tier 1) 50 40K 1M Scale (Tier 2) 1000 80K 2.5M Enterprise Custom Custom Custom
RPM = Requests per minute
TPM = Tokens per minute
TPD = Tokens per day
Check your tier: console.anthropic.com/settings/limits
Advanced Features Streaming Responses Watch Claude’s output in real-time:
forge task start 1 --llm claude --stream Vision Support Claude can analyze images:
forge task create \ --title "Implement this design" \ --attach mockup.png \ --llm claude Extended Thinking For complex problems, enable extended thinking:
{ "llms" : { "claude" : { "thinkingTokens" : 10000 } } } Comparison with Other Agents
Feature Claude 3.5 GPT-4 Gemini Pro Context 200K 128K 2M Reasoning ⭐⭐⭐⭐⭐ ⭐⭐⭐⭐ ⭐⭐⭐ Speed ⭐⭐⭐⭐ ⭐⭐⭐ ⭐⭐⭐⭐⭐ Cost $$$ $$$$ $$ Code Quality ⭐⭐⭐⭐⭐ ⭐⭐⭐⭐ ⭐⭐⭐⭐
Claude wins : Complex reasoning, architecture, security
GPT-4 wins : Consistency, documentation
Gemini wins : Speed, cost, context windowReal-World Examples Example 1: API Refactoring forge task create \ --title "Refactor REST API to GraphQL" \ --description " Current: 15 REST endpoints in src/api/ Goal: Single GraphQL endpoint with: - Schema matching REST capabilities - Resolvers for all queries/mutations - DataLoader for N+1 prevention - Maintain backward compatibility via REST wrapper " \ --llm claude Result : Claude created comprehensive GraphQL schema, resolvers, and maintained REST compatibility.Example 2: Security Audit forge task create \ --title "Security audit of payment processing" \ --description " Review src/payment/ for security issues: - Input validation - SQL injection - XSS vulnerabilities - Sensitive data exposure - Rate limiting " \ --llm claude Result : Claude identified 7 security issues with detailed explanations and fixes.Next Steps 
