Claude Code Commands Cheat Sheet (2026)

This cheat sheet covers the Claude Code commands people actually use: session commands, setup commands, review commands, integrations, MCP commands, agent skills, and CLI flags.

It combines the public command set with newer 2026 additions, while also noting hidden or leak-based command names that appear in source references.

If you want one clean reference instead of scattered changelogs and half-complete lists, this is the version to keep open beside your terminal.

Last audited: May 06, 2026

Session and Context Commands

Use these commands to manage conversation state, context size, checkpoints, and session history.

Setup, Config, and Environment Commands

Use these commands to configure Claude Code, manage memory, adjust permissions, and control the local environment.

Skills, Agents, Plugins, and MCP Commands

Use these commands to extend Claude Code with skills, agents, plugins, and connected MCP servers.

MCP Slash Command Pattern

Claude Code can generate commands dynamically from connected MCP servers:

/mcp__[server]__[prompt] [args]

Examples:

• /mcp__github__list_prs
• /mcp__github__create_pr
• /mcp__jira__create_issue
• /mcp__linear__get_sprint

These commands only appear after the relevant MCP server is connected.

Coding, Review, and Planning Commands

These commands are the ones most people use during real development work.

Git, PR, and Release Commands

These commands are related to branches, commits, pull requests, and release workflows.

Integration, Remote, and Device Commands

Use these commands when working across IDEs, browsers, desktops, mobile, or remote environments.

Diagnostics, Internal, and Experimental Commands

These are mostly internal, debug-oriented, experimental, or source-leak command names.

Claude Code CLI Commands and Flags

Many users searching for Claude Code commands actually want terminal commands. These are the main ones.

Core CLI Commands

Important CLI Flags

Useful Environment Variables

Real Workflows

Start a New Repository

/init
/status
/model

This initializes CLAUDE.md, checks the environment, and sets the model.

Onboard a New Teammate

/team-onboarding
/init
/memory

This is useful for turning existing local Claude Code usage into a ramp-up guide, then pairing it with the project’s CLAUDE.md and memory files.

Understand an Unfamiliar Codebase

/status
/context
/plan map the project structure and main entry points

This gives a quick environment check, shows loaded context, and builds a plan before editing anything.

Review a Pull Request

/review
/security-review
/pr-comments
/diff

This covers review, security, feedback, and final diff inspection.

Prepare a Safe Refactor

/review
/plan refactor the auth flow without changing behavior
/diff

This is a good sequence before touching critical code paths.

Manage a Long Session

/context
/compact keep decisions only
/cost

This checks context size, compacts it, and shows the cost impact.

Run a Multi-File Refactor

/review
/simplify
/batch rename OldThing NewThing

This is a clean sequence for review, simplification, and broad edits.

Fix a Bug in Stages

/debug trace the failing checkout flow
/review
/diff

This works well when the issue is unclear, and you want to inspect the final change carefully.

Work With PR Feedback

/pr-comments 123
/review
/diff

This is useful when you want to address reviewer comments and re-check the final patch.

Switch Between Tasks

/rename feature-auth
/clear
/resume feature-auth

This keeps sessions separate and makes it easier to return to a task later.

Set Up MCP and Use It Immediately

/mcp
/mcp__github__list_prs
/mcp__jira__create_issue

This goes from the MCP setup to the actual server commands quickly.

Work Across Devices

/remote-control
/remote-env
/teleport

This covers the main remote workflow commands in one place.

Learn What Changed After an Update

/powerup
/help
/release-notes

Use this after an update to check release changes, diagnose environment issues, and review any settings affected by the new version.

Review Usage and Limits

/usage
/cost
/stats

This is the quickest way to check activity, plan limits, and session cost.

Start a Headless One-Off Task

claude -p "review this diff and list risks"

Use this when you want one result and do not need an interactive session.

Run a Deep Cloud Review

/review
/ultrareview
/pr-comments

Use this when a normal review is not enough and you want a deeper cloud-based review pass before merging.

Reduce Repetitive Permission Prompts

/less-permission-prompts
/permissions
/hooks

Use this after a few real sessions to identify safe read-only commands and build a cleaner allowlist for future work.

Check Usage from Remote Control

/extra-usage
/context
/exit

This is useful when checking usage and session state from a Remote Control client without going back to the local terminal.

FAQs:

Q: What is Claude Code?
A: Claude Code is Anthropic’s terminal-based AI coding agent. It runs locally via the CLI (npm install -g @anthropic-ai/claude-code), reads and edits your actual project files, executes shell commands, runs tests, and manages git operations.

Q: What is the difference between a slash command and a prompt in Claude Code?
A: A prompt is what you type to give Claude a coding task: “refactor this function,” “write a test for this endpoint.” A slash command controls the session itself.

Q: What is CLAUDE.md and what goes in it?
A: CLAUDE.md is a Markdown file in your project root that Claude reads at the start of every session in that repository. It acts as a persistent project brief.

Q: What is the difference between /clear and /compact?
A: /clear deletes all conversation history. The context window is empty after running it, but file edits made during the session remain. /compact replaces conversation history with a compressed summary, preserving the thread of what was discussed. Use /compact when you want Claude to remember context from earlier in the session but need to free up token budget. Use /clear when you are switching to a completely different task and do not need any prior context.

Q: What does /plan actually do in Claude Code?
A: /plan toggles plan permission mode. In this mode, Claude proposes each tool action and waits for your approval before executing it. Use it when working in an unfamiliar codebase or before a large refactor you want to review step by step.

Q: How do I create a custom slash command in Claude Code?
A: Create a Markdown file at .claude/commands/[name].md in your project (for team-shared commands) or ~/.claude/commands/[name].md (for personal commands available in all projects). The filename without the .md extension becomes the command name. The file content is the prompt Claude receives when the command runs. Add a YAML-style frontmatter block at the top to specify which tools the command can use, which model to run it with, and a description that appears in /help. Use $ARGUMENTS in the file content to capture whatever text is passed after the command name.

Q: Can Claude Code connect to GitHub?
A: Yes, in two ways. First, /install-github-app sets up the Claude GitHub App, which lets Claude participate in pull request workflows via GitHub Actions. Second, connecting a GitHub MCP server via /mcp exposes GitHub API operations as slash commands directly in your session (e.g., /mcp__github__list_prs, /mcp__github__create_pr).

Q: How do I reduce costs when using Claude Code?
A: Several approaches work well in combination. Switch to Haiku for mechanical tasks (/model haiku) and back to Opus or Sonnet for complex reasoning. Use /effort low for quick iteration tasks where deep reasoning is not necessary. Use /usage as the main usage screen; /cost and /stats now open the relevant tabs inside it. For custom commands that run frequently, add model: haiku to the frontmatter.

Q: What is the difference between /doctor and /status in Claude Code?
A: /doctor actively tests your environment. It reports failures with actionable error messages. /status reads and displays your current configuration, such as the active model, permission mode, connected MCP servers, and tool state. Run /doctor after installation, after upgrading, or when Claude Code behaves unexpectedly. Run /status at the start of a session to confirm settings before starting work.

Q: Can Claude Code be used in a CI/CD pipeline?
A: Yes. Claude Code supports a non-interactive print mode (claude -p "your prompt") that executes a single prompt and exits, making it scriptable in any CI environment. The --output-format json flag structures the output for programmatic parsing. For GitHub specifically, /install-github-app sets up the official Claude GitHub Actions integration. The /hooks command also allows HTTP webhooks on lifecycle events, which can trigger external CI systems when Claude completes a task or uses a specific tool.

Q: What MCP servers work with Claude Code?
A: Any server that implements the Model Context Protocol can be connected. Once connected via /mcp, each server’s prompts appear as slash commands in the /mcp__[server]__[prompt] format.

Q: What is the difference between /focus and Ctrl+O in Claude Code?
A: As of v2.1.110, Ctrl+O only toggles between the normal and verbose transcript. Focus view is now controlled separately with /focus. If you want the cleaner, stripped-down focus view, use /focus. If you want transcript verbosity changes, use Ctrl+O.

Q: What does /effort do in Claude Code now?
A: /effort controls how much reasoning Claude uses for a task. As of v2.1.111, Opus 4.7 also supports xhigh, which sits between high and max. Running /effort without arguments now opens an interactive slider so you can adjust it visually.

Related Resources

• awesome-claude-code: A curated list of awesome tools, IDE integrations, frameworks, and other resources for developers working with Anthropic’s Claude Code.
• Best Agent Skills: 10 Best Free Agent Skills for Claude Code & AI Workflows.
• Claude Code Slash Commands Cheatsheet: The most complete, verified reference for every Claude Code slash command.
• OpenAI Codex Commands Cheat Sheet: CLI commands, slash commands, flags, config keys, environment variables, sandbox settings, MCP, and real workflows.
• AI Coding Agents: 7 Best CLI AI Coding Agents.
• Best Web Dev Tools: 10 Best Free AI Tools for Frontend Developers