Claude Code Guide

_For reference and contributions, visit the [official Claude Code documentation](https://code.claude.com/docs/en/overview)_ _Commands and provider model mappings change quickly; the linked official references remain authoritative._

| Section | Status | Other Resources | | ------------------------------------- | ------ | ------------------------------------------------------------------------------------------------------- | | Getting Started | ✅ | **Claude-Code** [Docs](https://code.claude.com/docs/en/overview) | | Configuration & Environment Variables | ✅ | **Claude-Code via** [**Discord**](https://github.com/zebbern/claude-code-discord) | | Commands & Usage | ✅ | Security Agents [SKILL.md](https://github.com/zebbern/claude-code-guide/tree/main/skills) | | Interface & Input | ✅ | Let Agent Create [SKILL.md](https://github.com/zebbern/agent-skills-authoring) | | Advanced Features | ✅ | 954+ Agent [Skills](https://github.com/zebbern/antigravity-awesome-skills) | | Automation & Integration | ✅ | No cost ai [resources](https://github.com/zebbern/no-cost-ai) | | Help & Troubleshooting | ✅ | 250+ Mermaid [templates](https://github.com/zebbern/mermaid-templates) | | Third-Party Integrations | ✅ | Discord Communication [MCP](https://github.com/zebbern/discord-mcp-agent) |

---

**Fast paths:** [Install](#quick-start) · [Commands](#claude-commands) · [Config](#configuration--environment) · [MCP](#mcp-integration) · [Agents](#sub-agents) · [Troubleshoot](#help--troubleshooting) | Area | Start here | Also useful | | --- | --- | --- | | [Getting Started](#getting-started) | [Quick Start](#quick-start) | [Initial Setup](#initial-setup), [System Requirements](#system-requirements) | | [Configuration](#configuration--environment) | [Environment Variables](#environment-variables) | [Configuration Files](#configuration-files) | | [Commands](#commands--usage) | [Slash Commands](#claude-commands) | [CLI Quick Reference](#cheat-sheet) | | [Interface](#interface--input) | [Keyboard Shortcuts](#keyboard-shortcuts) | [Vim Mode](#vim-mode) | | [Advanced Features](#advanced-features) | [Plan Mode](#plan-mode), [Auto Mode](#auto-mode), [MCP](#mcp-integration) | [Sub Agents](#sub-agents), [Skills](#skills), [Hooks](#hooks-system) | | [Security](#security--permissions) | [Security & Permissions](#security--permissions) | [Dangerous Mode](#dangerous-mode), [Best Practices](#security-best-practices-main) | | [Automation](#automation--integration) | [Automation & Scripting](#automation--scripting-with-claude-code) | [PR Review](#auto-pr-review-inline-comments), [Issue Triage](#issue-triage-suggest-labels--severity) | | [Help](#help--troubleshooting) | [Troubleshooting](#help--troubleshooting) | [Best Practices](#best-practices), [Monitoring](#monitoring--alerting) | | [Third-Party Integrations](#third-party-integrations) | [DeepSeek Integration](#deepseek-integration) | [Provider Setup Examples](#provider-setup-examples) |

Full content map

- **[Getting Started](#getting-started)** - [Quick Start](#quick-start) - [System Requirements](#system-requirements) - [Initial Setup](#initial-setup) - **[Configuration & Environment](#configuration--environment)** - [Environment Variables](#environment-variables) - [Configuration Files](#configuration-files) - **[Commands & Usage](#commands--usage)** - [Slash Command Reference](#claude-commands) - [CLI Quick Reference](#cheat-sheet) - **[Interface & Input](#interface--input)** - [Keyboard Shortcuts](#keyboard-shortcuts) - [Vim Mode](#vim-mode) - **[Advanced Features](#advanced-features)** - [Thinking Mode](#thinking-keywords) - [Effort Levels](#effort-levels) - [Advisor Tool](#advisor-tool) - [Fast Mode](#fast-mode) - [Auto Mode](#auto-mode) - [Plan Mode](#plan-mode) - [Background Tasks](#background-tasks) - [Workflows & Scheduling](#workflows--scheduling) - [Remote Sessions](#remote-sessions) - [Claude in Chrome](#claude-in-chrome) - [Desktop and IDEs](#desktop-and-ides) - [Sandbox Mode](#sandbox-mode) - [LSP Tool](#lsp-tool) - [Sub Agents](#sub-agents) - [Agent Teams](#agent-teams) - [Skills](#skills) - [Plugin System](#plugin-system) - [Worktree Isolation](#worktree-isolation) - [Native Installer](#native-installer) - [Authentication CLI](#claude-auth) - [Agent Management CLI](#claude-agents-cli) - [Remote Control](#remote-control) - [Managed Settings](#managed-settings) - [Model Updates](#model-updates) - [Theming & Customization](#theming--customization) - [Code Review](#code-review) - [Insights](#insights) - [MCP Integration](#mcp-integration) - [Hooks System](#hooks-system) - **[Security & Permissions](#security--permissions)** - [Dangerous Mode](#dangerous-mode) - [Security Best Practices](#security-best-practices-main) - **[Automation & Integration](#automation--integration)** - [Automation & Scripting](#automation--scripting-with-claude-code) - [Auto PR Review](#auto-pr-review-inline-comments) - [Issue Triage](#issue-triage-suggest-labels--severity) - **[Help & Troubleshooting](#help--troubleshooting)** - [Installation Issues](#installation--nodejs-issues) - [MCP Issues](#mcp-model-context-protocol-issues) - [Best Practices](#best-practices) - [Monitoring & Alerting](#monitoring--alerting) - **[Third-Party Integrations](#third-party-integrations)** - [Provider Setup Examples](#provider-setup-examples) - [DeepSeek Integration](#deepseek-integration)

---

Getting Started

**Enable completion alerts:** run `/config` inside Claude Code and choose a notification channel such as **Terminal bell**.

Quick Start

> [!TIP] > **Run claude in a project directory to start the interface.** > > **Go to [Help & Troubleshooting](#help--troubleshooting) to fix issues...** **Native installer (recommended; no Node.js required)** macOS, Linux, or WSL: ```bash curl -fsSL https://claude.ai/install.sh | bash ``` Windows PowerShell: ```powershell irm https://claude.ai/install.ps1 | iex ``` Windows CMD: ```bat curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd ``` Supported package managers (manual updates by default): ```bash brew install --cask claude-code winget install Anthropic.ClaudeCode ``` npm distribution (supported; Node.js 22+ is required to install): ```bash npm install -g @anthropic-ai/claude-code ``` Verify the installation, then start Claude Code: ```bash claude --version claude doctor claude ``` Native installs update themselves. Homebrew, WinGet, and the signed `apt`, `dnf`, and `apk` repositories follow their package manager's update flow. See the [official setup guide](https://code.claude.com/docs/en/setup) for channels, version pinning, Linux repository setup, and signature verification. For an npm install, upgrade with `npm install -g @anthropic-ai/claude-code@latest`; do not use `sudo npm install -g`. --- > [!Tip] > **Open Project Via Terminal Into VS Code / Cursor** > > ### $ - cd /path/to/project > > ### $ - code . > > **Make sure you have the (Claude Code extension) installed in your VS Code / Cursor** ---

System Requirements

> - OS: macOS 13+, Windows 10 1809+/Windows Server 2019+, Ubuntu 20.04+, Debian 10+, or Alpine Linux 3.19+. Native Windows, WSL 1, and WSL 2 are supported. > - Hardware: 4 GB+ RAM and an x64 or ARM64 processor > - Software: Git is optional on native Windows; without Git for Windows, Claude uses the PowerShell tool instead of Bash. Node.js 22+ is required only to install through npm; the installed CLI is a native binary. > - Internet: Connection for API calls ---

Initial Setup

Claude Code requires a Pro, Max, Team, Enterprise, or Console account; the free Claude.ai plan does not include Claude Code. The normal first-party flow is browser sign-in: ```bash claude auth login # Claude subscription claude auth login --console # Anthropic Console/API billing claude auth status # Verify the active login ``` For API automation or a provider/gateway deployment, inject credentials from an OS key store or secret manager instead of committing them: ```bash export ANTHROPIC_API_KEY="$SECRET_FROM_YOUR_STORE" # bash/zsh: current process only ``` ```powershell $env:ANTHROPIC_API_KEY = $secretFromYourStore # PowerShell: current process only ``` > [!Important] > A persistent `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or credential helper selects API/provider authentication even if you are logged in. Subscription-only features such as Remote Control, cloud sessions, claude.ai MCP connectors, and notification preferences then remain unavailable. Do not commit credentials; use your platform's secret storage. ---

Configuration & Environment

Environment Variables

> **Environment values can also be stored as strings under the `env` key in a `settings.json` file. The [official environment-variable reference](https://code.claude.com/docs/en/env-vars) is the exhaustive source.** > [!Important] > **On PowerShell, use `$env:NAME = "value"` for the current process. Persist secrets through an OS key store or secret manager, not a checked-in settings file.** ```bash # Authentication and routing: set only when API/provider billing is intentional export ANTHROPIC_API_KEY="$SECRET_FROM_YOUR_STORE" export ANTHROPIC_AUTH_TOKEN="$TOKEN_FROM_YOUR_STORE" export ANTHROPIC_BASE_URL="https://gateway.example.com" export ANTHROPIC_CUSTOM_HEADERS="X-Trace-Id: 12345" # Model selection and provider alias overrides export ANTHROPIC_MODEL="sonnet" export ANTHROPIC_DEFAULT_FABLE_MODEL="" export ANTHROPIC_DEFAULT_OPUS_MODEL="" export ANTHROPIC_DEFAULT_SONNET_MODEL="" export ANTHROPIC_DEFAULT_HAIKU_MODEL="" # Third-party provider selection (enable only one deployment path) # export CLAUDE_CODE_USE_BEDROCK=1 # export ANTHROPIC_BEDROCK_REGION_PREFIX=eu # Prefer eu/us/apac/jp/au/global cross-region inference on Bedrock # export CLAUDE_CODE_USE_VERTEX=1 # export CLAUDE_CODE_USE_FOUNDRY=1 # Timeouts and output budgets, in milliseconds/tokens export API_TIMEOUT_MS=1200000 export BASH_DEFAULT_TIMEOUT_MS=120000 export BASH_MAX_TIMEOUT_MS=600000 export MCP_TIMEOUT=30000 export MCP_TOOL_TIMEOUT=60000 export MAX_MCP_OUTPUT_TOKENS=25000 export MAX_THINKING_TOKENS=0 # 0 disables fixed thinking where supported; positive values set a budget # Session, context, agents, and accessibility # export CLAUDE_CODE_SIMPLE=1 # export CLAUDE_CODE_SAFE_MODE=1 export CLAUDE_CODE_DISABLE_1M_CONTEXT=1 # Clamp native-1M models to 200K via autocompaction; warns if the clamp is not enforced export CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1 # Opt out of enforcing the assumed context window for unknown model IDs export CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS=20 export CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=3 export CLAUDE_CODE_FORWARD_SUBAGENT_TEXT=1 export CLAUDE_AX_SCREEN_READER=1 # Feature and administration controls export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 export CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1 export CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1 export CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE=1 export ENABLE_CLAUDEAI_MCP_SERVERS=false # Network routing export HTTP_PROXY="http://proxy.example.com:8080" export HTTPS_PROXY="http://proxy.example.com:8080" export NO_PROXY="localhost,127.0.0.1" # Privacy/network reduction: these are presence-based; unset them to turn them off export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 export DISABLE_TELEMETRY=1 export DISABLE_ERROR_REPORTING=1 ``` The block is a catalog, not a recommended profile—do not enable mutually exclusive provider variables together. Boolean variables usually accept `1`/`true` and `0`/`false`, but the three presence-based variables shown at the end treat any non-empty value, including `0`, as enabled. Environment values in `settings.json` override the shell value at startup and when the file changes.

Global Config Options

Use `/config` for interactive settings, or pass one or more `key=value` pairs. Run `/config --help` for the keys supported by your installed build. ```bash /config # Open the settings UI /config theme=dark model=sonnet # Update supported keys directly ``` For version-controlled or managed configuration, edit JSON settings files directly: | Scope | File | | :---- | :--- | | User | `~/.claude/settings.json` | | Project (shared) | `.claude/settings.json` | | Project (private) | `.claude/settings.local.json` | | Managed | macOS: `/Library/Application Support/ClaudeCode/`
Linux/WSL: `/etc/claude-code/`
Windows: `C:\Program Files\ClaudeCode\` | ```json { "model": "sonnet", "theme": "dark", "autoUpdatesChannel": "stable", "permissions": { "defaultMode": "default" } } ``` Settings precedence is **managed policy → CLI arguments/`--settings` → local → project → user**. Permission arrays have their own merge rules, so read the [settings reference](https://code.claude.com/docs/en/settings) before relying on ordinary last-writer-wins behavior. `~/.claude.json` stores global state, session/trust data, and local/user MCP configuration; it is not the user settings file.

Configuration Files

Claude Code combines human-authored instructions from several locations: | Memory Type | Location | Purpose | Use Case Examples | Shared With | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------- | -------------------------------------------------------------------- | ------------------------------- | | **Enterprise policy** | macOS: `/Library/Application Support/ClaudeCode/CLAUDE.md`
Linux: `/etc/claude-code/CLAUDE.md`
Windows: `C:\Program Files\ClaudeCode\CLAUDE.md` | Organization-wide instructions managed by IT/DevOps | Company coding standards, security policies, compliance requirements | All users in organization | | **Project memory** | `./CLAUDE.md` or `./.claude/CLAUDE.md` | Team-shared instructions for the project | Project architecture, coding standards, common workflows | Team members via source control | | **User memory** | `~/.claude/CLAUDE.md` | Personal preferences for all projects | Code styling preferences, personal tooling shortcuts | Just you (all projects) | | **Project memory (local)** | `./CLAUDE.local.md` | Personal project-specific preferences (git-ignored) | Your sandbox URLs, preferred test data, personal overrides | Just you (current project) | | **Project rules** | `.claude/rules/**/*.md` | Modular project rules (loaded alongside CLAUDE.md) | Linting rules, API conventions, path-scoped standards | Team members via source control | > Instruction files are concatenated rather than overriding one another. User and ancestor-project files load at startup; `CLAUDE.md` files in subdirectories load lazily when Claude works there. `CLAUDE.md` is context, not an enforcement boundary. Use `@path` to import another file. Claude Code does not load `AGENTS.md` automatically; add `@AGENTS.md` to `CLAUDE.md` (or use a symlink where portable) when you want to share those instructions. #### `.claude/rules/` Directory The `.claude/rules/` directory lets you break project instructions into separate Markdown files instead of one large `CLAUDE.md`. Markdown files are discovered recursively. Add `paths` frontmatter with glob patterns when a rule should load only for matching files. This is useful for: - **Modular organization**: Separate concerns (e.g., `api-conventions.md`, `testing-rules.md`) - **Per-directory overrides**: Nested `rules/` directories can apply scoped rules - **Team collaboration**: Different team members can own different rule files via PR review #### Auto-Memory Claude can save useful working context under `~/.claude/projects//memory/`. It loads the first 200 lines or 25 KB of `MEMORY.md`; use `/memory` to inspect, edit, disable, or remove saved memories. Auto-memory is machine-local and shared across worktrees for the same repository. Auto-memory is most useful for context you would otherwise repeat across sessions: - Preferred build, test, and lint commands - Local conventions that are not obvious from code alone - Architecture decisions that influence future edits - Team preferences that should shape how Claude proposes changes Keep durable team rules in `CLAUDE.md` or `.claude/rules/`. Treat auto-memory as helpful working context, not as the only source of truth. ---

Commands & Usage

Slash Command Reference

Command Line Flags

| Flag / Command | Description | Example | | :--------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------- | | `-d, --debug` | Enable debug mode (shows detailed debug output). | `claude -d -p "query"` | | `--include-partial-messages` | Include partial streaming events; requires print mode and `stream-json`. | `claude -p --output-format stream-json --include-partial-messages "query"` | | `--include-hook-events` | Include hook lifecycle events in `stream-json` output. | `claude -p --output-format stream-json --include-hook-events "query"` | | `--forward-subagent-text` | Forward subagent text/thinking with `parent_tool_use_id` in `stream-json`. | `claude -p --output-format stream-json --forward-subagent-text "query"` | | `--verbose` | Override verbose mode setting from config (shows expanded logging / turn-by-turn output). | `claude --verbose` | | `-p, --print` | Print response and exit (useful for piping output). | `claude -p "query"` | | `--output-format ` | Output format (only works with `--print`): `text` (default), `json` (single result), or `stream-json` (realtime streaming). | `claude -p "query" --output-format json` | | `--input-format ` | Input format (only works with `--print`): `text` (default) or `stream-json` (realtime streaming input). | `claude -p --output-format stream-json --input-format stream-json` | | `--replay-user-messages` | Re-emit user messages from stdin back to stdout for acknowledgment — **only works with** print mode plus `stream-json` input and output. | `claude -p --verbose --input-format stream-json --output-format stream-json --replay-user-messages` | | `--allowedTools`, `--allowed-tools ` | Comma/space-separated permission rules to allow. | `claude --allowed-tools "Bash(git *)" "Edit"` | | `--disallowedTools`, `--disallowed-tools ` | Comma/space-separated permission rules to deny. | `claude --disallowed-tools "Edit"` | | `--mcp-config ` | Load MCP servers from JSON files or strings (space-separated). | `claude --mcp-config ./mcp-servers.json` | | `--strict-mcp-config` | Only use MCP servers from `--mcp-config`, ignoring other MCP configurations. | `claude --mcp-config ./a.json --strict-mcp-config` | | `--append-system-prompt ` | Append a system prompt to the default system prompt (useful in print mode). | `claude -p --append-system-prompt "Do X then Y"` | | `--autocompact ` | Override the auto-compaction window for this session. | `claude --autocompact 500k` | | `--ax-screen-reader` | Use a flat, screen-reader-friendly renderer without decorative borders or animations. | `claude --ax-screen-reader` | | `--bare` | Minimal scripted mode: skip discovered hooks, skills, plugins, MCP, auto-memory, and `CLAUDE.md`. | `claude --bare -p "query"` | | `--permission-mode ` | Start in `default`/`manual`, `acceptEdits`, `auto`, `dontAsk`, `bypassPermissions`, or `plan`. | `claude --permission-mode plan` | | `--permission-prompt-tool ` | Specify an MCP tool to handle permission prompts in non-interactive mode. | `claude -p --permission-prompt-tool mcp_auth_tool "query"` | | `--fallback-model ` | In print mode, try a comma-separated fallback chain when the primary model is unavailable. | `claude -p --fallback-model sonnet,haiku "query"` | | `--effort ` | Set effort to `low`, `medium`, `high`, `xhigh`, or `max`, or start session-only `ultracode` mode where supported. | `claude --effort high` | | `--model ` | Model for the current session. Accepts aliases like `sonnet`/`opus` or a full model ID when pinning. | `claude --model sonnet` | | `--advisor ` | Set the experimental advisor for this session without changing `advisorModel`; intentionally omitted from `claude --help`. | `claude --advisor opus` | | `--settings ` | Load additional settings from a JSON file or a JSON string. | `claude --settings ./settings.json` | | `--add-dir ` | Additional directories to allow tool access to. | `claude --add-dir ../apps ../lib` | | `--ide` | Automatically connect to an IDE on startup if exactly one valid IDE is available. | `claude --ide` | | `-c, --continue` | Continue the most recent conversation in the current directory. | `claude --continue` | | `-r, --resume [sessionId]` | Resume a conversation; provide a session ID or interactively select one. | `claude -r "abc123"` | | `--session-id ` | Use a specific session ID for the conversation (must be a valid UUID). | `claude --session-id 123e4567-e89b-12d3-a456-426614174000` | | `--agents ` | Define custom subagents dynamically via JSON (see subagent docs for format). | `claude --agents '{"reviewer":{"description":"Reviews code","prompt":"..."}}'` | | `--agent ` | Specify a specific agent for the current session. | `claude --agent my-custom-agent` | | `--bg` | Start or continue work as a background session that can be viewed from `claude agents`. | `claude --bg "fix failing tests"` | | `--bg --exec ` | Run a shell command as an attachable background session. | `claude --bg --exec "npm test"` | | `--name ` | Name a background or remote session for easier identification. | `claude --bg --name nightly-check "run checks"` | | `--chrome` | Enable Chrome browser integration for web automation and testing. | `claude --chrome` | | `--no-chrome` | Disable Chrome browser integration for this session. | `claude --no-chrome` | | `--cloud [description\|session\|url]` | Create or attach to a Claude Code web session on claude.ai. | `claude --cloud "Fix the login bug"` | | `--remote` | Deprecated alias for `--cloud`. | `claude --remote "Fix the login bug"` | | `--remote-control`, `--rc` | Start an interactive local session that can also be controlled from claude.ai or the Claude app. | `claude --remote-control "My Project"` | | `--teleport [session]` | Resume a web session in your local terminal. | `claude --teleport ` | | `--fork-session` | When resuming, create a new session ID instead of reusing the original. | `claude --resume abc123 --fork-session` | | `--json-schema ` | Get validated JSON output matching a JSON Schema after agent completes (print mode only). | `claude -p --json-schema '{"type":"object",...}' "query"` | | `--max-budget-usd ` | Maximum dollar amount to spend on API calls before stopping (print mode only). | `claude -p --max-budget-usd 5.00 "query"` | | `--max-turns ` | Limit the number of agentic turns (print mode only). Exits with error when limit reached. | `claude -p --max-turns 3 "query"` | | `--betas ` | Beta headers to include in API requests (API key users only). | `claude --betas interleaved-thinking` | | `--tools ` | Restrict which built-in tools Claude can use. Use "" to disable all, "default" for all, or specific tool names. | `claude --tools "Bash,Edit,Read"` | | `--system-prompt ` | Replace the entire system prompt with custom text (works in interactive and print modes). | `claude --system-prompt "You are a Python expert"` | | `--system-prompt-file ` | Load a system prompt from a file, replacing the default in interactive or print mode. | `claude --system-prompt-file ./custom-prompt.txt` | | `--append-system-prompt-file ` | Load additional system-prompt text from a file in interactive or print mode. | `claude --append-system-prompt-file ./extra-rules.txt` | | `--plugin-dir ` | Load a plugin directory or `.zip` for this session only (repeatable). | `claude --plugin-dir ./my-plugin --plugin-dir ./other.zip` | | `--plugin-url ` | Fetch a plugin `.zip` URL for this session only (repeatable). | `claude --plugin-url https://example.com/plugin.zip` | | `--setting-sources ` | Comma-separated list of setting sources to load (user, project, local). | `claude --setting-sources user,project` | | `--no-session-persistence` | Disable session persistence so sessions are not saved to disk (print mode only). | `claude -p --no-session-persistence "query"` | | `--disable-slash-commands` | Disable all skills and slash commands for this session. | `claude --disable-slash-commands` | | `--dangerously-skip-permissions` | Skip normal permission prompts, subject to non-bypassable safety checks and managed policy. | `claude --dangerously-skip-permissions` | | `--safe-mode` | Disable user/project customizations for configuration troubleshooting while retaining authentication, models, tools, and permissions. | `claude --safe-mode` | | `--worktree [name]`, `-w [name]` | Start in `/.claude/worktrees/`; omit the name to generate one. | `claude -w feature-auth` | | `--from-pr [value]` | Filter/resume sessions by PR number or GitHub/GitLab/Bitbucket PR/MR URL, or open the picker. | `claude --from-pr 123` | | `--init` | Run Setup hooks with the `init` matcher before a print-mode session. | `claude -p --init "query"` | | `--init-only` | Run Setup hooks and exit. | `claude --init-only` | | `--maintenance` | Run Setup hooks with the `maintenance` matcher before a print-mode session. | `claude -p --maintenance "query"` | | `-v, --version` | Show the installed `claude` CLI version. | `claude --version` | | `-h, --help` | Display help / usage. | `claude --help` | > This table highlights common and recently changed options; `claude --help` and the [live CLI reference](https://code.claude.com/docs/en/cli-reference) are authoritative. `--output-format json` is useful for one-shot automation; use `stream-json` for event-level integrations. For programmatic integrations, the former **Claude Code SDK** is now the [Claude Agent SDK](https://platform.claude.com/docs/en/agent-sdk/overview): TypeScript uses `@anthropic-ai/claude-agent-sdk`, and Python uses `claude-agent-sdk` / `claude_agent_sdk`. Use `claude -p` for headless CLI calls; `--bare` removes discovered customization and keychain/OAuth access for low-overhead API/provider automation.

CLI Quick Reference & Configuration Examples

```md ## Claude Cheat Sheet # Start and resume claude # Start interactive REPL claude "explain this project" # Start REPL seeded with a prompt claude -p "summarize README.md" # Non-interactive headless print mode cat logs.txt | claude -p "explain" # Pipe input to Claude and exit claude -c # Continue most recent conversation claude -r "" "finish this" # Resume by ID or name claude --model sonnet # Pick the Sonnet alias for this run claude --model opus # Pick the Opus alias for harder tasks # Install, update, and auth claude update # Manually update Claude Code claude doctor # Diagnose install/version & setup claude install stable # Install/reinstall the native binary on the stable channel claude auth login # Log in to your Anthropic account claude auth status # Check authentication status claude auth logout # Log out # Background and remote sessions claude agents # Open the live session dashboard: running, blocked, completed claude agents --json # Scriptable JSON list of live/background sessions claude --bg "run the integration suite and summarize failures" # Start a background session claude --bg --exec "npm test" # Run a shell command as an attachable background session claude attach # Attach to a background session claude logs # Print recent background-session output claude stop # Stop a background session claude rm # Remove it from agent view and delete its worktree; transcript remains resumable claude remote-control # Serve local sessions to web/mobile while this process stays alive claude --cloud "Fix the bug" # Create a web session on claude.ai claude --teleport # Copy a web session into this terminal # Config essentials /config # Interactive settings /config model=sonnet # Set a supported key directly /config theme=dark /config --help # Show settable keys and values # For shared or managed settings, edit the appropriate settings.json file. # MCP essentials claude mcp list # List configured MCP servers claude mcp get # Show details for a server claude mcp add [args...] # Add local stdio server claude mcp add --transport http # Add remote HTTP server claude mcp login # Complete OAuth without opening /mcp claude mcp logout # Clear saved OAuth credentials claude mcp reset-project-choices # Reset approvals for project .mcp.json servers claude mcp serve # Run Claude Code itself as an MCP stdio server # High-value flags claude --add-dir ../apps ../lib # Add additional working directories claude --allowed-tools "Bash(git log *)" "Read" # Allow listed tools without permission prompts claude --disallowed-tools "Edit" # Deny listed tools claude -p "query" --output-format json # Structured one-shot output claude --verbose # Verbose logging (turn-by-turn) claude --dangerously-skip-permissions # Skip permission prompts (use with caution) claude --permission-mode plan # Start in plan mode without source edits claude --effort high # Set reasoning effort for this session claude --bare -p "query" # Fast scripted call without discovered customization claude --safe-mode # Troubleshoot with user/project customization disabled claude --ax-screen-reader # Use the accessible flat-text renderer claude --max-turns 3 -p "query" # Limit agentic turns (print mode only) claude --json-schema '{"type":"object"}' -p "query" # Get validated JSON output claude --chrome # Enable Chrome browser integration claude --agent code-reviewer # Run this session with a named agent claude ultrareview 123 --json # Non-interactive comprehensive review for PR/target 123 # Slash shortcuts claude --fork-session -r abc123 # Fork instead of reusing original claude -w feature-auth "implement feature" # Start in an isolated git worktree /rename auth-refactor # Name current session /resume # Open session picker /export output.md # Export conversation to file /branch experiment-name # Branch the current conversation /fork "investigate the flaky test" # Copy conversation into a background session /subtask "trace the regression" # Fork a subagent that reports back here /cd ../other-project # Move the current session without losing its cache /review high --fix # Run /code-review via its current alias /goal "all tests pass and README is updated" # Keep working until the completion condition is met /loop 30m "check deploy health and summarize anomalies" # Schedule recurring work /workflows # View dynamic workflows and background orchestration # Settings precedence: managed policy > CLI/--settings > local > project > user. ``` ---

Interface & Input

Keyboard Shortcuts

Text Editing

Multiline Input

Quick Commands

Vim Mode

> [!Note] > Enable vim-style editing from `/config` -> Editor mode.

Vim Mode Switching

| Command | Action | From mode | | :------ | :-------------------------- | :-------- | | `Esc` | Enter NORMAL mode | INSERT | | `i` | Insert before cursor | NORMAL | | `I` | Insert at beginning of line | NORMAL | | `a` | Insert after cursor | NORMAL | | `A` | Insert at end of line | NORMAL | | `o` | Open line below | NORMAL | | `O` | Open line above | NORMAL | | Command | Action | | :-------------- | :------------------------ | | `h`/`j`/`k`/`l` | Move left/down/up/right | | `w` | Next word | | `e` | End of word | | `b` | Previous word | | `0` | Beginning of line | | `$` | End of line | | `^` | First non-blank character | | `gg` | Beginning of input | | `G` | End of input |

Vim Editing

Command History

> Claude Code maintains command history for the current session: ``` * History is stored per working directory * Cleared with `/clear` command * Use Up/Down arrows to navigate (see keyboard shortcuts above) * **Ctrl+R**: Reverse search through history (if supported by terminal) * **Note**: History expansion (`!`) is disabled by default ``` ---

Advanced Features

Thinking Keywords

> [!Note] > **`ultrathink` is the only documented prompt keyword for a one-turn request for deeper reasoning.** Phrases such as `think`, `think hard`, and `think harder` are ordinary prompt text; they are not graduated Claude Code controls. Use `/effort` for an explicit session setting. `ultrathink` adds an in-context instruction for that turn without changing the effort value sent to the API. ```md Ultrathink. Propose a step-by-step strategy to fix flaky payment tests and add guardrails. ```

Effort Levels

Use `/effort` to tune how much reasoning the selected model applies before answering. Higher effort levels are best for planning-heavy work, deep reviews, and long-context tasks. ```bash /effort # Open the effort picker /effort low # Faster, lighter reasoning /effort medium # Balanced default for many tasks /effort high # Deeper planning and review /effort xhigh # Strong default for difficult coding and agentic work where supported /effort max # Session-only maximum; test for diminishing returns /effort ultracode # Session-only xhigh plus dynamic workflow orchestration, where available /effort auto # Return to the selected model's default ``` Available levels depend on the model. The saved `effortLevel` setting accepts `low` through `xhigh`; `max` normally applies only to the current session, although `CLAUDE_CODE_EFFORT_LEVEL=max` can force it for sessions launched with that environment variable. `ultracode` is a separate session-only mode that combines `xhigh` with standing dynamic-workflow orchestration, so it requires workflows and an xhigh-capable model. Prefer the lowest effort that reliably solves the task because higher effort increases latency and token use.

Advisor Tool (Experimental)

The advisor pairs the main model with a second, at-least-as-capable model that Claude may consult at important planning, debugging, or completion decisions. Each consultation sends the full conversation, including tool calls and results; it counts toward subscription usage or is billed at the advisor model's API rates. ```bash /advisor # Open the picker and save the user default /advisor opus # Save Opus as the advisor /advisor off # Clear the saved advisorModel setting claude --advisor opus # Use Opus for this session without changing the saved default ``` The feature runs only through the first-party Anthropic API, for subscription or API-billed accounts; it is unavailable on Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry. Claude decides when to consult it. `advisorModel` is the persistent settings key, while the intentionally hidden `--advisor` launch flag is session-only. Fable 5 is not currently selectable as an advisor. See the [advisor guide](https://code.claude.com/docs/en/advisor) for supported main/advisor pairings.

Fast Mode

> [!Note] > **Fast mode is a research preview that runs the same Opus model and capabilities up to 2.5× faster at a higher price per token. It does not trade model quality for speed.** ```bash /fast # Toggle in the CLI # Option+O on macOS or Alt+O on Windows/Linux also toggles it ``` Fast mode currently supports **Opus 5 and Opus 4.8**. It is unavailable for Sonnet, Haiku, Opus 4.7, third-party providers, and the VS Code extension. Subscription users need usage credits; Team and Enterprise also require Owner enablement. Use it for latency-sensitive interactive work, and standard mode for cost-sensitive or long autonomous tasks. Lower `/effort` is the separate control that may trade reasoning depth for speed.

Auto Mode

Auto mode lets Claude evaluate and approve lower-risk actions automatically while still blocking or asking on higher-risk operations. It is useful for trusted development loops where repeated permission prompts slow down work. ```bash # Start in auto mode, or cycle to it with Shift+Tab claude --permission-mode auto # Inspect the built-in and effective classifier configuration claude auto-mode defaults claude auto-mode config # Remove a cached/custom classifier config and return to defaults claude auto-mode reset # Add --yes to skip confirmation ``` ```json { "autoMode": { "allow": ["$defaults"], "soft_deny": ["$defaults"], "hard_deny": [] } } ``` Key points: - Auto mode is available by default on every supported provider; `CLAUDE_CODE_ENABLE_AUTO_MODE` is now a no-op compatibility variable. - The classifier trusts the working directory and current repository remotes by default. Add organization infrastructure under `autoMode.environment` only when needed. - Put `autoMode` in user settings, managed settings, or `--settings`. Repository `.claude/settings.json` and `.claude/settings.local.json` cannot inject classifier policy. - Use `"$defaults"` to extend built-in `allow`, `soft_deny`, `hard_deny`, or `environment` rules instead of replacing them. - Explicit `permissions.deny` and content-scoped `permissions.ask` rules are evaluated before the classifier. Use those for non-negotiable blocks or huma > 内容过长，已截断。完整文档请查看仓库原文。