Claude Code & API Reference for Builders

Practical, up-to-date guides on Claude Code, the Anthropic API, and the Agent SDK — for developers who build with Claude.

Claude Tool Use: Advanced Patterns for Production

Advanced Claude tool use patterns: parallel tool calls, forced tool choice, tool error handling, streaming with tools, and structured output via tools.

Automatic Model Routing: Route Claude Requests to the Right Model at Runtime

How to build a lightweight classifier that automatically routes each Claude API request to Haiku, Sonnet, or Opus based on task complexity — with full code.

How to Write Effective CLAUDE.md Files (With 12 Real Examples)

What actually belongs in a CLAUDE.md file, what doesn't, and 12 real-world examples annotated with what each pattern is doing and why.

Haiku vs Sonnet vs Opus: Which Claude Model for Your Use Case (April 2026)

A decision tree plus nine concrete use cases showing which Claude model is the right default, what you pay, and when you should escalate or downshift.

Claude Code vs Cursor: Which AI Coding Tool in 2026?

Side-by-side comparison of Claude Code CLI and Cursor IDE for real development work — architecture differences, pricing, and when to use each.

How to Use Claude Code Subagents for Parallel Research

A practical guide to Claude Code's Explore subagent, multi-agent fan-out, and when spawning parallel subagents actually saves time versus a single-thread sweep.

Claude Code Permissions: Trust Levels, Allow Lists, and Safe Defaults

How Claude Code's permission system works — trust levels, allowed/disallowed tools, per-project settings, and how to configure safe defaults for your workflow.

Claude Code Hooks: Automate and Control Every Tool Call

How to configure Claude Code hooks — shell commands that fire before or after tool use — with real examples for logging, enforcement, and automation.

Claude Code CLI Commands: Full Reference (2026)

Every Claude Code CLI flag, slash command, and keyboard shortcut — with usage examples and when to use each.

Claude API Pricing 2026: Complete Breakdown with Calculators

Full Claude API pricing table for April 2026 — Haiku, Sonnet, Opus, caching, batching, 1M context — with worked cost examples for common workloads.

Claude API Error Handling: Rate Limits, Retries, and Production Patterns

Every Claude API error code explained with production retry strategies, exponential backoff implementation, and circuit breaker patterns.

From $800 to $120/month: A Claude API Cost Optimization Case Study

How a SaaS team reduced their Claude API bill by 85% in 6 weeks without quality loss — step-by-step with exact numbers and the changes that moved the needle.

Claude Agent SDK Quickstart: Build Your First Agent in 15 Minutes

Step-by-step guide to building a working Claude agent with tool use using the Anthropic SDK — Python and TypeScript, with copy-paste code.

Claude 1M Context Window: What It Can Do and What It Costs

Everything you need to know about Claude's 1M token context window — what fits in it, what it costs, when to use it, and when not to.

Running Claude Code across multiple repos without losing context

A concrete workflow for working with Claude Code on 3+ repositories simultaneously — what works, what doesn't, and the one setting that makes it tractable.

Claude prompt caching: when it pays off and when it doesn't (2026 numbers)

The actual break-even math for Claude prompt caching in 2026, with measured examples. A 5-minute cache needs 2 reuses to save money; a 1-hour cache needs 4.