Claude Code Guide

Getting started with Claude Code — installing it, signing in, configuring your editor, feeding it files, and running your first session.

The tools that sit alongside Claude Code — editor integrations, MCP servers for files, GitHub, browsers, databases and Slack, and a full Git workflow.

Managing context, keeping memory, and tuning Claude to hold on to what matters across sessions

Working with more flow, using the agents, skills, MCP servers and plugins that extend what Claude Code can do.

From vibe coding to production in eight phases: quality gates, testing, an OWASP security audit, performance, QA, deployment, monitoring and A/B testing

Agent SDK, headless mode, scripting and automating your flow

Enforce your rules with machinery rather than by asking. All 33 events, the JSON contract a hook receives and answers with, what each exit code means, and examples you can paste in as they are.

The same engine runs in the CLI, the desktop app, the browser, on your phone and inside your IDE. What each surface can do, how work moves between them, and which plan unlocks what.

Getting Claude Code to work when nobody is typing: claude -p in a script, the three scheduling mechanisms that are genuinely different, claude-cli:// links in a runbook, GitHub Actions and the Agent SDK.

The two ways to extend Claude Code that people most often confuse. A skill is knowledge loaded when it is needed; a subagent is work handed to a separate context. Which to reach for, and every frontmatter field.

All six permission modes and which one your sessions actually start in, the rule syntax that quietly opens more than you meant, the OS-enforced Bash sandbox, and what no mode ever auto-approves.

Finding the root cause of a loop with 5 Whys, anti-loop patterns, profiling, error taxonomy, retry, circuit breakers, graceful shutdown, and handling a production incident