The advice I find myself repeating every time someone asks how to get started with Claude Code
Configuration Sandboxing - constrain file access and network connections Permissions - pre-approve safe operations, hard-block dangerous ones Agent rules - concise, scoped CLAUDE.md files that shape agent behaviour Recommended plugins & tools - 3rd party tools that improve safety, context usage and code navigation Extend knowledge and capabilities Skills - dynamic knowledge acquisition with progressive disclosure Language servers - give the agent go-to-definition, find-references, and type checking MCP tools - external tool servers, used sparingly Workflow Plan before acting - read-only exploration and task definition Embrace starting fresh sessions - keep context clean Template out common commands - reusable prompts for common tasks ...