Gemini CLI cheatsheet

Vertex AI also requires GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION.

System requirements: Node.js 20+, macOS 15+, Windows 11 24H2+, or Ubuntu 20.04+

Set with -m flash or GEMINI_MODEL env var.

# MCP server management
$ gemini mcp add <name> <cmd-or-url>
$ gemini mcp remove <name>
$ gemini mcp list
$ gemini mcp enable <name>
$ gemini mcp disable <name>

# Extension management
$ gemini extensions install <source>
$ gemini extensions uninstall <name>
$ gemini extensions list
$ gemini extensions update [name] [--all]
$ gemini extensions enable/disable <name>
$ gemini extensions link <path>
$ gemini extensions new <path>

# Skills management
$ gemini skills list [--all]
$ gemini skills install <source>
$ gemini skills link <path>
$ gemini skills uninstall <name>
$ gemini skills enable/disable <name>

# Hooks
$ gemini hooks migrate

Exit codes: 0 Success · 1 Error · 42 Bad input · 53 Turn limit exceeded

Include file or directory content in your prompt:

# Include a file
@src/main.ts fix the bug on line 42

# Include a directory
@src/ what does this module do?

# Include multiple paths
@package.json @src/ audit dependencies

Git-aware: respects .gitignore for directory inclusion.

# Run a single shell command
!ls -la

# Toggle persistent shell mode
!

# Shell output injected into context
!git diff HEAD~1

GEMINI_CLI=1 is set in all shell subprocesses.

/rewind or press Esc twice to open the rewind dialog:

Applies only to AI-made file changes, not manual edits or ! shell commands.

Save and restore named checkpoints to explore multiple approaches:

# 1. Save current state
/resume save my-decision-point

# 2. Try approach A...

# 3. Restore to saved state
/resume resume my-decision-point

# 4. Try approach B...

# Show all loaded context
/memory show

# Force reload all context files
/memory reload

# Append text to global GEMINI.md
/memory add "Always use TypeScript strict mode"

# Generate project GEMINI.md
/init

Create .geminiignore in project root (follows .gitignore syntax):

# Exclude a directory
/packages/

# Exclude specific files
apikeys.txt
*.log

# Exclude all .md except README
*.md
!README.md

Files are hidden from CLI tools but remain visible to Git and other services.

# Add stdio server
$ gemini mcp add myserver npx -y my-mcp-package

# Add HTTP server
$ gemini mcp add myserver https://api.example.com/mcp

# Add with options
$ gemini mcp add myserver cmd --transport http --trust --timeout 30000

# List all servers
$ gemini mcp list

# Remove a server
$ gemini mcp remove myserver

# Enable / disable
$ gemini mcp enable myserver
$ gemini mcp disable myserver --session

Reference MCP resources in prompts:

# Reference a resource
@server://resource/path summarize this

# Slash commands from MCP prompts
/prompt-name --arg=value

Skills provide on-demand expertise — loaded only when activate_skill is called.

Discovery locations (precedence):

# List all skills
$ gemini skills list --all

# Install from Git or local
$ gemini skills install https://github.com/org/skill
$ gemini skills install ./local-skill

# Link for development
$ gemini skills link ./my-skill

# Enable / disable
$ gemini skills enable my-skill
$ gemini skills disable my-skill

Save reusable prompts as slash commands.

File locations:

• User: ~/.gemini/commands/
• Project: .gemini/commands/

# .gemini/commands/git/commit.toml
description = "Generate commit message"
prompt = """
Generate a conventional commit message for:

!{git diff --staged}

{{args}}
"""

Command becomes /git:commit. Subdirectory / → : namespace.

Placeholders:

Read-only (always available):

• read_file, list_directory, glob
• grep_search, google_web_search
• web_fetch (with confirmation)
• codebase_investigator, cli_help
• ask_user

Write (restricted):

• write_file, replace — only for .md files inside plans directory

Memory:

• save_memory, activate_skill

1. Set goal
   └─ natural language or /plan <goal>

2. Discuss strategy
   └─ Gemini may ask clarifying questions

3. Review plan
   └─ Markdown file written to plans dir
   └─ Ctrl+X to edit in external editor

4. Approve or iterate

5. Switch to YOLO/auto_edit to implement

Auto model routing: Pro during planning → Flash during implementation.

Persist in ~/.bashrc, ~/.zshrc, or .gemini/.env.

All hooks receive JSON via stdin:

{
  "session_id": "...",
  "transcript_path": "/path/to/transcript",
  "cwd": "/project/dir",
  "hook_event_name": "BeforeTool",
  "timestamp": "2026-01-01T00:00:00Z"
}

Respond with JSON on stdout:

BeforeTool extra: hookSpecificOutput.tool_input overrides args.

AfterTool extra: hookSpecificOutput.additionalContext appended to result.

BeforeAgent extra: hookSpecificOutput.additionalContext appended to prompt.

Environment vars available: GEMINI_PROJECT_DIR, GEMINI_SESSION_ID, GEMINI_CWD