Skip to main content
Run pool to open an interactive session. The agent can read your code, run commands, and write files. It asks for approval before taking action unless you switch to Allow all mode. For one-shot tasks and scripts, see Automate tasks instead.
This documentation describes Poolside Agent CLI v1.0.13. Check your version with pool --version. To update, exit any active session and run pool update from your terminal. See Poolside Agent CLI releases on GitHub for release history.

​
Start a session

Open a session in your current directory:
Open a session in a specific directory:
Run a session in a Git worktree for a branch, creating the worktree and branch if needed:
Use --worktree without a branch name to let pool generate a worktree name:
When your terminal supports it, pool notifies the terminal of the worktree directory. New tabs, panes, or splits can open in that directory, so you can run git diff or other commands while the session continues running. The shell that started pool remains in its original working directory. To add a prefix to generated worktree names, set pool.worktree_prefix in ~/.config/poolside/settings.yaml. Require a configured sandbox for the Poolside agent server:
Use --sandbox disabled only when you want to run without a configured sandbox. Open the session picker to resume a previous session from the current directory:
Open the agent server picker to choose a configured ACP-compatible agent server for the session:
Resume a specific session by ID (a session ID is provided when you exit a session):
By default, pool uses the credentials saved by pool login. To authenticate one invocation with an API key, set POOLSIDE_API_KEY before the command:
To override the saved API URL for one invocation, set POOLSIDE_API_URL before pool. If an MCP server needs input from environment variables, start pool with those variables set:

​
Write prompts

Type your prompt in the input area at the bottom and press Enter to send. To find the newline shortcut for your terminal, press ? with an empty input field. Common shortcuts are:
  • macOS: Shift+Enter when your terminal supports key disambiguation, or Alt+Enter as a fallback. In Apple’s built-in Terminal app, if Alt+Enter does not insert a new line, go to Terminal > Settings > Profiles > select your profile > Keyboard, then enable Use Option as Meta key.
  • Linux: Shift+Enter when your terminal supports key disambiguation, or Alt+Enter as a fallback.
  • Windows: Shift+Enter when supported by your terminal, or Ctrl+Enter as a fallback. Use Alt+Enter when connected over SSH.
Use the up and down arrow keys to browse prompt history for the current directory. Type ! to enter shell mode and run a command directly from the prompt input box. You can select text in the conversation output using your terminal’s selection controls. When your terminal supports it, double-click and drag to select whole words.

​
Add context

Type @ in the prompt to mention a file or directory. pool opens a picker so you can choose what to include. When the connected model supports image input, the agent can view PNG, JPEG, GIF, and WebP image files in your project that are 5 MB or smaller. To add an image from your clipboard, paste it into the prompt input box with Ctrl+V.

​
Use a skill

Type $ at the start of the prompt or after a space to open the skill picker. Continue typing to filter the list, then press Tab or Enter to insert the selected skill reference into your prompt. When you send the prompt, the selected skill applies to that turn. For more information, see Skills.

​
Answer agent questions

If the agent needs clarification while it is working, it can open a question dialog instead of guessing. To trigger this flow, tell the agent to ask when needed, for example Ask me a question if anything is ambiguous. You can select one of the provided options or choose Type your own answer to enter a custom response. Press Esc to decline.

​
Notifications

pool can send notifications when a turn ends, when an approval prompt needs your response, or when the agent asks a question. Notifications appear only when the pool session is not focused. When you run pool in cmux, pool can also show notifications and status icons.

​
Status line

The status line shows session details such as the current mode, Git branch, working directory, and model when that information is available. Click the mode or model to open the corresponding selector. Click the current directory to open it in your configured editor. When the connected agent server offers thought-level choices, the status line shows the current choice next to the model. Click it, or use /thought-level or /effort, to select a reasoning effort level. Available choices depend on the connected agent server and model.

​
Approve tool actions

When the agent wants to run a command or write a file, it asks for approval:
  • Allow once: Approve only that action
  • Always allow: …: Save an approval rule for similar actions for the rest of the session
  • Accept edits for this session: For file write approvals, switch to Accept edits mode for the rest of the session
  • Reject: Decline and let the agent work around it if possible
To approve all actions automatically, start the session with --mode always-allow, or switch to Allow all mode with /mode. For persistent approval rules, path rules, and settings.yaml locations, see Permissions.

​
Modes

When you use the Poolside agent server, these modes are available: Press Shift+Tab to cycle through modes, or use /mode to open the mode selector. When you select a mode, pool asks whether to save it as the default.

​
Use plan mode

Use plan mode when you want to review an implementation approach before the agent changes your code. It is useful for complex refactors, broad changes that span multiple files, or work where early decisions are hard to undo. In plan mode, the agent can read and explore your codebase, ask clarifying questions, and write an implementation plan for you to review. Plan mode does not modify source files. To enter plan mode, type /plan, type /mode plan, or press Shift+Tab to cycle to plan mode. To leave plan mode, switch back to build mode with /mode default or Shift+Tab. When you switch from build mode into plan mode, pool remembers the approval mode you were using. When you switch back to build mode, pool restores that approval mode. When the plan is ready, approve the prompt to switch to build mode, or decline it to keep reviewing or discussing the plan. Declining keeps the agent in plan mode and does not cancel the task. pool saves each plan as a Markdown file. Outside a sandbox, pool stores the plan in your local Poolside state directory. In a sandbox, it stores the plan at .poolside/plans/ in your current workspace. The saved path is clickable in the terminal so you can open the plan in your editor.

​
Keyboard shortcuts

CLI shortcuts use the key names shown by your terminal. On macOS, use Ctrl for CLI shortcuts such as Ctrl+M, Ctrl+C, and Ctrl+V. Command shortcuts are handled by your terminal application, not by pool. Press ? with an empty input field to see the shortcut list for your terminal.

​
Picker and menu shortcuts

​
Slash commands

Type / to open the command menu, or type a command directly. The commands you see can include terminal UI commands and commands from the connected agent server. Non-Poolside ACP servers can expose a different set of server-provided slash commands. These commands are built into the pool interface: When you use the Poolside agent server, these additional commands are available: You can also ask pool about its own commands, capabilities, and current behavior. The Poolside agent server uses a built-in introspection skill to answer questions about itself.

​
Change the agent

Press Ctrl+M or Alt+M, or use /model to change the agent for the current session or set a new default. The command is named /model because Agent Client Protocol refers to agents, as defined in Poolside, as models. After you select a model, pool asks whether to save it as the default. To start a session with a specific model:

​
Get debug logs

Use /logs when you need to collect debug logs for troubleshooting or support. /logs creates a logs.zip archive for the current session and prints links to copy the archive, copy the archive path, or open the containing folder. The archive can include session logs, ACP logs, trajectory data, and session metadata. Review the archive before sharing it, because logs and trajectory data can include prompt and response text from the session.

​
Rewind a turn

Press Esc, then Esc while idle, or use /rewind to roll back the last turn. Rewind removes that exchange from the conversation history so the agent does not see it on the next prompt.

​
Sessions

pool saves sessions automatically. When you exit, pool prints the --resume command for that session so you can continue it later. Use /resume during a session to open the session picker and switch to another saved session. You cannot resume a session while a turn is in progress. Use /rename to rename the current session. The session picker opened by pool -r or pool --resume shows renamed sessions from the current directory by default. Press Tab in the picker to switch between current-directory sessions and sessions from all directories.

​
MCP servers

Use /mcp to see MCP servers, connection status, and tools for the current session.

​
View the trajectory

When you use the Poolside agent server, use /share during a session to get a link to the web-based trajectory viewer. After a session, browse trajectory files locally:

​
Send feedback

Use /feedback to open a feedback draft for the current session. You can choose whether to attach logs. To attach an earlier session, resume it first with pool -r, then run /feedback.