Verified
New since your last visit
Unverified

Reference for the Antigravity CLI (agy) and its core extensibility surface. Official documentation at antigravity.google/docs.

TUI & Keys

Global controls

ItemDescription
#EscClose active panels, halt streams, or clear an empty prompt
#Ctrl+CTerminate the CLI session
#Ctrl+DExit the session, only when the prompt box is empty
#Ctrl+LRefresh and clear the visual terminal buffer

Prompt focus

ItemDescription
#EnterSubmit your prompt or the active menu selection
#Shift+Enter / Ctrl+JInsert a newline without submitting
#Ctrl+VPaste media files or clipboard blocks into the prompt
#Ctrl+OExpand or collapse detailed tool reasoning output
#Ctrl+ROpen the Artifact Review Panel
#Ctrl+GLaunch your default $EDITOR to compose the prompt
#Alt+JSwitch focus to the next subagent awaiting confirmation
#Ctrl+KInstantly approve the pending subagent action
#Ctrl+A / Ctrl+EMove the cursor to the start or end of the line
#Ctrl+Z / Ctrl+Shift+ZUndo or redo the last text edit in the prompt
#F5Start or stop voice dictation
#Alt+F / Alt+BMove the cursor forward or back one word
#Ctrl+W / Alt+Backspace / Alt+DDelete the word before or after the cursor

Navigation & scrolling

ItemDescription
# / Scroll highlighted selections up or down by one item
#PgUp / Shift+↑Scroll the active text viewport up by one page
#PgDn / Shift+↓Scroll the active text viewport down by one page
# / Swap pages inside multipage panels like the Session Picker
#TabConfirm the highlighted slash-command autofill option

Tool confirmations

ItemDescription
#yAuthorize the proposed tool, command, or artifact
#nReject the proposed tool, command, or artifact
#AApprove all generated artifacts, inside the Review Panel

Slash Commands (Core)

Session lifecycle

ItemDescription
#/helpOpen the help panel of commands and shortcuts
#/exit / /quitClose the TUI session and restore your host shell
#/clear / /newResets active conversation contexts, not just the display
#/rewind / /undoRoll back conversation history to a previous message
#/fork / /branchClone the current conversation thread into a new parallel session
#/rename <name>Rename the current session thread
#/resume / /switch / /conversationOpen the conversation picker overlay to load a previous thread

Configuration & account

ItemDescription
#/config / /settingsOpen the interactive Settings Editor Overlay
#/modelChoose your preferred reasoning model for the session
#/permissionsOpen the interactive tool permissions manager panel
#/planningEnable multi-turn plan generation for complex tasks
#/fastEnable fast mode, bypassing reasoning plans for quick actions
#/keybindingsOpen the interactive Keyboard Shortcut Editor
#/statuslineOpen the Status Bar customization overlay
#/title [on/off]Toggle or set terminal window title updates
#/creditsView remaining G1 credits and purchase links
#/logoutDisconnect your profile and purge auth tokens from the keyring

Slash Commands (Tools)

Tools & tasks

ItemDescription
#/agentsOpen the Agent Manager Panel for background subagents
#/artifactOpen the Artifact Review Panel
#/hooksBrowse active pre-flight/post-format script hooks
#/mcpOpen the Model Context Protocol server manager
#/skillsBrowse loaded local and global Agent Skills
#/tasksOpen the Task Manager Panel for background shell logs

Reasoning & collaboration

ItemDescription
#/boost <task>Run on-demand multi-agent deep reasoning loops
#/teamwork-preview / /teamworkLaunch collaborative multi-agent teams for long-horizon work

Utilities

ItemDescription
#/add-dir <path>Add a directory path to the active workspace
#/btw <query>Ask a side question without interrupting the main thread
#/contextOpen the context usage visualization panel
#/copyCopy the last agent response to the clipboard
#/diffOpen the Interactive Diff Viewer
#/feedbackOpen the feedback submission panel
#/open <path>Force the path open in your default system editor
#/remote-control [on/off]Toggle a session-scoped Remote Control link for the active terminal session
#/usage / /quotaDisplay model quota usage
#/voice / /recordDictate a prompt using your microphone

CLI & Subcommands

Session flags

ItemDescription
#agyLaunch an interactive Antigravity CLI coding session
#-c / --continueContinue the most recent conversation session
#--conversation <id>Resume a previous conversation by its unique ID
#-p / --print / --promptRun prompt non-interactively and print response to stdout
#-i / --prompt-interactiveExecute initial prompt and continue interactive session
#--model <name>Specify model for current CLI session
#--effort <level>Set reasoning effort for session (low, medium, high)
#--mode <mode>Set agent execution mode (accept-edits, plan)
#--remote-controlStart the session with a Remote Control connection for another device

Workspace & sandbox

ItemDescription
#--project <id>Project ID or project name for current CLI session
#--new-projectInitialize a new project state for current session
#--add-dir <path>Add directory to workspace context (repeatable flag)
#--agent <name>Specify agent role or persona for current session
#--sandboxRun inside sandbox with terminal execution restrictions
#--dangerously-skip-permissionsAuto-approve tool permission requests without prompting

Piping & output

ItemDescription
#--input-format <fmt>Input format for print mode (text, stream-json)
#--output-format <fmt>Output format for print mode (text, json, stream-json)
#--json-schema <schema>Enforce structured output using JSON schema string or file
#--print-timeout <dur>Timeout for a print-mode run; unset, the run continues until the response completes
#--disable-slash-commandsDisable slash command and skill expansion in print mode
#--log-file <path>Override CLI log file path

Subcommands

ItemDescription
#agy modelsList available models and reasoning configurations
#agy agents / agy agentList available subagent roles and configurations
#agy mcp <cmd>Manage MCP servers (add, remove, list, enable, disable)
#agy plugin <cmd>Manage plugins (install, list, import, validate)
#agy changelogShow changelog and release notes for installed CLI
#agy installConfigure environment paths and shell completions
#agy updateUpdate CLI binary to latest available release
#agy mic-serveServe host microphone input to CLI on another host
#agy remote-controlManage remote-control background daemon (start, status, stop)

Settings (settings.json)

Appearance & editing

ItemDescription
#colorSchemeTUI color theme, default "terminal"
#altScreenModeScreen buffer mode: default, always, or never
#editorExternal editor target: auto, vim, emacs, or custom
#editorModePrompt editing model: default (flat) or vim (modal)
#vimInsertFirstStart Vim mode in Insert; requires editorMode: "vim"
#verbosityVisual verbosity: high (full output) or low (minimal)
#runningLightSpeedProgress animation speed: fast, medium, slow, off

Safety & permissions

ItemDescription
#toolPermissionGlobal safety preset, default "request-review"
#artifactReviewPolicyCode review policy: asks-for-review, agent-decides, always-proceed
#allowNonWorkspaceAccessLet file read/write tools navigate outside the workspace root
#enableTerminalSandboxRestrict local execution commands to OS containment rings

Notifications & account

ItemDescription
#notificationsDesktop and terminal bell chime on task completion
#showTipsShow agentic tips above the prompt panel while generating
#showFeedbackSurveyShow periodic quality feedback surveys after tasks
#useG1CreditsUse personal AI credits once plan quotas are exhausted
#enableTelemetryAllow metric collection and crash log streaming

Environment Variables

Authentication

ItemDescription
#GEMINI_API_KEYAuthenticate with a Gemini API key instead of Google sign-in
#GOOGLE_GEMINI_BASE_URLPoint the CLI at a different Gemini-compatible endpoint

Rules & Skills

Project rules

ItemDescription
#~/.gemini/GEMINI.mdGlobal rules applied across every workspace
#.agents/rules/*.mdWorkspace-level rule files, 12,000 characters each
#Manual / Always On / Model Decision / GlobThe four rule activation modes

Custom skills

ItemDescription
#.agents/skills/<name>/SKILL.mdWorkspace-level skill definition with YAML frontmatter
#~/.gemini/config/skills/Global machine-wide custom skills directory
#progressive disclosureOnly a skill's name and description load until it's activated

Hooks & MCP

Lifecycle hooks

ItemDescription
#hooks.jsonConfig file in .agents/ or ~/.gemini/config/ mapping hooks to events
#PreToolUseFires before a tool executes
#PostToolUseFires after a tool finishes
#PreInvocationFires before calling the model
#PostInvocationFires immediately after the model responds
#StopFires when execution terminates

Plugins

ItemDescription
#plugins/<name>/plugin.jsonManifest bundling skills, rules, and MCP configurations
#agy plugin listList all installed, enabled, and imported plugins
#agy plugin import geminiImport plugin bundle from Gemini ecosystem
#agy plugin import claudeImport compatible plugin bundle from Claude ecosystem

Model Context Protocol

ItemDescription
#mcp_config.jsonConfiguration registering external MCP tool servers
#agy mcp add <name> <cmd>Register an MCP server with executable command and flags
#agy mcp listDisplay configured MCP servers and connection status
#agy mcp enable <name>Enable a previously registered MCP server
#agy mcp disable <name>Disable an MCP server without removing its configuration
No matches — clear search to see everything.