Claude Code Complete Guide

Claude Code is a terminal-based AI coding agent. This handbook is for advanced users who want to run it as an operating system for software work: multiple sessions, explicit plans, automated checks, project memory, subagents, hooks, MCP tools, and repeatable team workflows.

Latest Update Baseline

• Treat v2.1.181~v2.1.190 as an operations and safety refresh: sandbox.credentials, destructive-command sandbox auto-approval, Windows PowerShell sandbox fixes, MCP login/logout, MCP idle timeout, Korean paste handling, non-interactive fallback stability, and app/schema bug fixes.
• Track model restrictions and warnings: main model restrictions now center on Opus, Sonnet, Haiku, and Fable families; Haiku is not available as the main model but can be used for subagents, and deprecated model warnings are stronger.
• Keep subagent depth and background work bounded: v2.1.184 caps agent nesting at three levels, and later fixes improve nested agent, background session, Agent deny-rule, and permission-prompt reliability.
• Use Fable 5 for the hardest and longest-running autonomous tasks when your organization has access. It requires Claude Code v2.1.170 or later, is selected with /model fable, and is not the default model.
• Treat Opus 4.8 as the default high-capability Opus path for complex architecture, multi-step refactors, and long-running agentic work when Fable is unavailable or not appropriate.
• Check model aliases by provider. best uses Fable 5 where available and otherwise falls back to the latest Opus model; opus maps to Opus 4.8 on the Anthropic API, and sonnet maps to Sonnet 4.6. Other providers may lag behind unless you pin a full model name or ANTHROPIC_DEFAULT_*_MODEL.
• Plan for Fable-specific fallback. Claude Code automatically reroutes Fable requests flagged by safety classifiers to the default Opus path; use --safe-mode when repository context itself may be triggering a classifier.
• Use Agent View and background sessions for parallel work: claude agents, /bg, /background, claude --bg, and claude --bg --exec.
• Configure fallbackModel chains for availability failures before long autonomous sessions so overloads fail over deliberately instead of stopping the turn.
• Use /goal for completion-condition driven work and /workflows for dynamic workflows that orchestrate many background agents.
• Prefer /usage-credits over legacy /extra-usage, and use /reload-skills when commands or skills change during a session.
• Use native installation paths first; treat npm installation as legacy where official tooling does.
• Keep every agent session scoped to a concrete working directory, branch, and verification target.
• Prefer worktrees for parallel implementation, review, and experiment tracks.
• Put durable project rules in CLAUDE.md, but keep them short enough that the agent can obey them.
• Use subagents for bounded parallel work, not for urgent blocking decisions.
• Use hooks and MCP only after the manual workflow is clear enough to automate.
• Make verification part of the prompt contract: tests, lint, typecheck, browser checks, or review notes.

Handbook Map