Learning path
Claude Code Fundamentals
From first session through project instructions, permissions, planning, Git, testing, and MCP.
- 1Getting startedClaude Code is Anthropic’s agentic coding CLI: you give a task in a repo, it reads context, edits files, runs commands, and iterates with your approval boundaries.
- 2CLAUDE.mdCLAUDE.md is a project instruction file Claude Code reads so it follows your repo’s conventions without being reminded every session.
- 3PermissionsClaude Code permissions define which tools and actions the agent may take without asking—and which require human approval.
- 4PlanningAsk Claude Code for a short plan and file list before it edits, so you can reject bad approaches cheaply.
- 5Git workflowUse a branch-per-task Git workflow with Claude Code so agent commits stay reviewable and reversible.
- 6Verification gatesA verification gate is a deterministic check that must pass before agent work is accepted.
- 7What MCP isMCP (Model Context Protocol) is a standard way for AI clients to connect to external tools and data through servers.
- 8Parallel agentsParallel agents only help when tasks are partitioned, isolated on disk, and integrated through reviewable merges.