Vincent Type to start searching
How does Claude Code understand your requests, invoke tools, and self-recover step by step? A source-code deep dive into the Agent Loop's core architecture — streaming responses, parallel tool execution, auto-compaction, and error recovery.
A complete guide to Claude Code's configuration file system — five config sources, their file paths, priority rules, array merging vs value overriding, and enterprise managed settings delivery.
A thorough breakdown of Claude Code's permissions configuration — allow/deny/ask rule arrays, wildcard syntax, MCP tool permissions, defaultMode options, and additionalDirectories.
A thorough breakdown of Claude Code's hooks configuration — four hook types, core events (PreToolUse/PostToolUse/Stop/Notification), stdin/stdout protocol, exit code semantics, and practical examples.
A comprehensive guide to the remaining settings.json fields in Claude Code — env variable injection, model configuration, authentication helpers, Git attribution, session cleanup, language and UI, thinking depth, auto-updates, memory system, and more.
Create custom sub-agents for code exploration, architecture planning, and more — each with its own role, tools, and instructions.
API not connecting? MCP broken? /doctor auto-detects installation, connectivity, and config issues — here's how to fix them fast.
Simple rename? Set effort to low. Complex refactor? Crank it to max. Here's how /effort saves tokens without losing quality.
See real-time API costs, model pricing, and token breakdowns per session — /cost helps you make every dollar count.
Export conversations to files or clipboard for sharing, archiving, and review — so no valuable AI discussion goes to waste.
AI broke your code? /rewind rolls back both code and conversation to any point — your safety net when things go wrong.
Install, enable, and manage plugins that add custom commands, skills, agents, and hooks — build your own AI development toolkit.