1 min read
Terminal CLI - Claude Code
The primary command-line entry point for Claude Code sessions.
Reference Hub
Claude Code Field Guide
Commands, tools, hooks, MCP, subagents, teams, permissions, and workflow details organized into one practical reference.
17 entries
Start Here
Core workflow, modes, shortcuts, and day-one setup.
1 min read
Interactive Mode - Claude Code
Real-time prompt loop with history, completions, and multiline input.
1 min read
Keyboard Shortcuts - Claude Code
50+ customizable shortcuts for cancel, history, transcript, and more.
1 min read
Default Permission Mode - Claude Code
Approve each action manually - the safest mode for new tasks.
1 min read
Plan Mode - Claude Code
Explore and propose changes without executing them.
1 min read
Bypass Permissions Mode - Claude Code
Skip all permission checks. Container and VM use only.
1 min read
Permission Rules - Claude Code
Granular allow/ask/deny rules per tool with wildcard patterns.
1 min read
Sandboxing - Claude Code
Filesystem and network isolation for Bash tool calls on Linux and macOS.
1 min read
Model Aliases - Claude Code
Use opus, sonnet, haiku, and best to switch models easily.
1 min read
OpusPlan Alias - Claude Code
Hybrid mode: Opus for planning, Sonnet for execution.
1 min read
Effort Levels - Claude Code
Low, medium, high, xhigh, and max for adaptive reasoning control.
1 min read
Model Picker (/model) - Claude Code
Interactive UI to switch models and effort sliders mid-session.
1 min read
Custom Model Option - Claude Code
Add gateway or custom models to the picker via environment variables.
1 min read
Disable Model Invocation - Claude Code
Hide skills from Claude's auto-selection until manually triggered.
1 min read
PermissionRequest Hook - Claude Code
Fires when a permission dialog appears. Auto-approve or auto-deny.
1 min read
PermissionDenied Hook - Claude Code
Fires when auto mode or a rule denies an action.
1 min read
Plan Approval - Claude Code
Require lead approval before teammates execute their tasks.
21 entries
Tools
Bash, edit, read, grep, glob, notebook, LSP, and command behavior.
1 min read
Vim Editor Mode - Claude Code
Full vim keybindings (normal and insert modes) for prompt editing.
1 min read
Bash Mode - Claude Code
Prefix prompts with ! to run shell commands directly, bypassing Claude.
1 min read
Read Tool - Claude Code
Read file contents with line limiting, offset, and binary support.
1 min read
Write Tool - Claude Code
Create or overwrite files; requires permission for existing paths.
1 min read
Edit Tool - Claude Code
Targeted edits to specific sections without rewriting entire files.
1 min read
MultiEdit - Claude Code
Batch edit multiple files in a single atomic operation.
1 min read
Notebook Edit - Claude Code
Modify Jupyter notebook cells directly without touching JSON.
1 min read
Glob Tool - Claude Code
File discovery via pattern matching across the repository.
1 min read
Grep Tool - Claude Code
Search file contents by pattern with regex support.
1 min read
LSP Tool - Claude Code
Jump to definitions, find references, and type-check via language servers.
1 min read
Bash Tool - Claude Code
Execute shell commands with persistent working directory in project bounds.
1 min read
PowerShell Tool - Claude Code
Native PowerShell execution on Windows and optionally Unix hosts.
1 min read
Monitor Tool - Claude Code
Background monitoring of logs, files, and long-running processes.
1 min read
WebFetch Tool - Claude Code
Fetch and parse content from URLs, including JS-rendered pages.
1 min read
WebSearch Tool - Claude Code
Perform web searches and return ranked results with snippets.
1 min read
Accept Edits Mode - Claude Code
Auto-approve file edits and common filesystem commands.
1 min read
Subagent Tool Restrictions - Claude Code
Limit which tools a subagent can access.
1 min read
PreToolUse Hook - Claude Code
Fires before any tool executes. Allow, deny, defer, or modify the call.
1 min read
PostToolUse Hook - Claude Code
Fires after a successful tool call. Good for feedback and follow-ups.
1 min read
PostToolUseFailure Hook - Claude Code
Fires on tool execution errors for logging, alerting, and retry.
1 min read
MCP Tool Search - Claude Code
Deferred tool loading reduces context overhead for large MCP suites.
20 entries
Hooks
Lifecycle events, approvals, prompts, compacting, and automation points.
1 min read
Prompt Suggestions - Claude Code
Context-aware follow-up suggestions derived from git history.
1 min read
Prompt Caching - Claude Code
Automatic reuse of cached context for substantial cost reduction.
1 min read
Auto Compaction - Claude Code
Background context summarization when the window starts filling up.
1 min read
Hooks System - Claude Code
Event-driven automation with 20+ lifecycle events.
1 min read
SessionStart Hook - Claude Code
Fires when a session begins; load env vars and initialize state.
1 min read
SessionEnd Hook - Claude Code
Fires when a session terminates.
1 min read
UserPromptSubmit Hook - Claude Code
Fires before Claude processes user input; can validate or block.
1 min read
UserPromptExpansion Hook - Claude Code
Fires when a slash command expands; can block or inject context.
1 min read
SubagentStart and SubagentStop Hooks - Claude Code
Fire when subagents spawn and finish.
1 min read
TaskCreated and TaskCompleted Hooks - Claude Code
Fire on task lifecycle events.
1 min read
Stop Hook - Claude Code
Fires when Claude finishes responding. Can prevent the stop.
1 min read
FileChanged Hook - Claude Code
Fires when watched files change on disk.
1 min read
ConfigChange and InstructionsLoaded Hooks - Claude Code
Fire when settings or CLAUDE.md files change during a session.
1 min read
PreCompact and PostCompact Hooks - Claude Code
Fire before and after context compaction.
1 min read
Elicitation Hook - Claude Code
Fires when an MCP server requests input from the user.
1 min read
Command Hooks - Claude Code
Run shell scripts on events with environment variable passing.
1 min read
Prompt-Based Hooks - Claude Code
Use Claude itself to handle hook logic instead of shell scripts.
1 min read
Agent-Based Hooks - Claude Code
Spawn subagents to handle complex hook logic.
1 min read
Async Hooks - Claude Code
Run hooks in the background without blocking the session.
1 min read
MCP Prompts - Claude Code
Execute MCP prompts as commands via the slash menu.
7 entries
MCP
Servers, resources, prompts, OAuth, scopes, and managed MCP setup.
1 min read
Subagent MCP Scoping - Claude Code
Route specific MCP servers only to specific subagents.
1 min read
MCP Servers - Claude Code
Connect external tools and data sources via the open MCP standard.
1 min read
MCP Installation Scopes - Claude Code
Local, project, user, and plugin-level MCP configurations.
1 min read
MCP OAuth - Claude Code
Pre-configured or dynamic OAuth for remote MCP servers.
1 min read
MCP Resources - Claude Code
Reference and read resources exposed by MCP servers.
1 min read
MCP Channel Messaging - Claude Code
Receive push messages from MCP servers via channels.
1 min read
Managed MCP - Claude Code
Admin-controlled allow and deny lists for MCP servers.
11 entries
Subagents
Definitions, tools, memory, context isolation, and team patterns.
1 min read
Skill in Subagent - Claude Code
Run a skill in an isolated context via fork mode.
1 min read
Subagents - Claude Code
Spawn isolated workers with independent context windows.
1 min read
Built-in Subagents - Claude Code
Researcher, auditor, reviewer, and other ready-made subagent types.
1 min read
Custom Subagent Types - Claude Code
Create reusable subagent definitions at project or user level.
1 min read
Subagent Frontmatter - Claude Code
Configure model, tools, MCP, skills, memory, and scoping.
1 min read
Subagent Persistent Memory - Claude Code
Auto-memory that persists across multiple subagent invocations.
1 min read
Subagent Context Isolation - Claude Code
Prevent bloating the main conversation with research or exploration.
1 min read
Resume Subagents - Claude Code
Continue a subagent's work across sessions.
1 min read
Agent Teams - Claude Code
Coordinate multiple Claude Code instances with a shared task list.
1 min read
Team Lead - Claude Code
Coordinator agent that assigns tasks and synthesizes findings.
1 min read
Subagent Definitions as Teammates - Claude Code
Reuse custom subagent types as Agent Teams members.
11 entries
Skills And Memory
Skills, frontmatter, invocation, auto-memory, and reusable context.
1 min read
CLAUDE.md Files - Claude Code
Persistent project instructions loaded every session; supports nested dirs.
1 min read
.claude/rules Directory - Claude Code
Path-specific rules that only load for matching files.
1 min read
Auto Memory - Claude Code
Automatic session-to-session memory of build commands, errors, and learnings.
1 min read
Memory Command - Claude Code
View and edit auto-memory and CLAUDE.md via the /memory command.
1 min read
Skills System - Claude Code
Reusable markdown files with instructions and workflows.
1 min read
Bundled Skills - Claude Code
/simplify, /batch, /debug, /fast, and other built-in skills.
1 min read
Skill Invocation - Claude Code
Trigger with /skillname or let Claude auto-load when relevant.
1 min read
Skill Frontmatter - Claude Code
Configure model, effort, tools, MCP servers, and invocation scope.
1 min read
Skill Arguments - Claude Code
Pass arguments to skills with string substitution support.
1 min read
Skill Pre-Approval - Claude Code
Pre-approve tools before a skill executes so it runs without prompts.
1 min read
Live Skill Discovery - Claude Code
Changes to skill files are detected and reloaded automatically.
25 entries
Reference
Everything else that does not fit a tighter section.
1 min read
Background Tasks - Claude Code
Run Bash commands with Ctrl+B and retrieve output by task ID.
1 min read
Command History - Claude Code
Per-directory prompt history with Ctrl+R reverse search.
1 min read
Voice Dictation - Claude Code
Hold-to-record voice input on macOS, Linux, and Windows.
1 min read
Multiline Input - Claude Code
Shift+Enter, Option+Enter, or backslash+Enter for multi-line prompts.
1 min read
Side Questions with /btw - Claude Code
Ask quick side questions without derailing the main task.
1 min read
Environment Variable Persistence - Claude Code
SessionStart hooks can persist env vars across Bash tool calls.
1 min read
Git Integration - Claude Code
Stage, commit, branch, and open PRs without leaving the session.
1 min read
Worktrees - Claude Code
Isolated git worktrees for parallel Claude Code sessions.
1 min read
PR Status in Footer - Claude Code
Clickable PR link in the footer with review state color coding.
1 min read
gh CLI Integration - Claude Code
Full GitHub CLI support for automated PR and issue workflows.
1 min read
AGENTS.md - Claude Code
Define custom subagent types within your project's memory layer.
1 min read
Context Window Visualization - Claude Code
Interactive timeline showing what's in context at each turn.
1 min read
Auto Mode - Claude Code
Eliminate prompts with a background classifier that judges safety.
1 min read
DontAsk Mode - Claude Code
Only pre-approved tools allowed. Fully non-interactive for CI.
1 min read
Protected Paths - Claude Code
Auto-guarded directories like .git, .claude, and .vscode.
1 min read
1M Token Context - Claude Code
Extended context window for Opus and Sonnet on supported plans.
1 min read
Fast Mode - Claude Code
2.5x faster Opus at a higher token cost (research preview).
1 min read
Extended Thinking - Claude Code
Toggle with Alt+T. Claude reasons through complex problems before responding.
1 min read
Shared Task List - Claude Code
Teammates claim and complete work independently from one list.
1 min read
Inter-Agent Messaging - Claude Code
Teammates communicate directly without routing through the lead.
1 min read
Split Pane Display - Claude Code
Run each teammate in its own tmux or iTerm2 pane.
1 min read
Task Dependencies - Claude Code
Pending tasks depend on others and unblock automatically.
1 min read
/loop Command - Claude Code
Run a prompt repeatedly on a fixed interval or self-paced.
1 min read
Scheduled Tasks (Desktop) - Claude Code
GUI-based scheduling on your local machine for recurring work.
1 min read
Routines (Web) - Claude Code
Managed scheduling on Anthropic infrastructure with API and GitHub triggers.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever