Skip to content
TraeIDE

Search

Popular pages

No matching pages

Try a tool name or a topic such as pricing or MCP.

English

Cline CLI Guide

Cline’s terminal agent for interactive work, headless tasks and configurable providers.

Last verified: · How we verify
Coding agentClinemacOSWindowsLinux

Suitable workflows

Cline users extending their editor workflow into scripts and terminal sessions.

Limitations and billing

Review auto-approval settings before running tasks; headless execution can change files and run commands.

Capabilities we verified

Agent workflowCLI surfaceMCPBring your own key

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

Pricing & usage

See official pricing

Provider usage or Cline account billing. The cost of metered usage or an external agent can be separate from the subscription.

Check official pricing ↗

Models & access

Cline Provider, ClinePass or your own supported provider credentials.

Official model information ↗

Install and start the CLI

Follow the current official CLI installation guide for your platform and runtime.

Installation command · npm

npm install -g cline

Open your project folder in a terminal, then run:

cline --auto-approve false
Official installation instructions ↗

Account and authentication

Use cline auth to choose the provider, model and account credentials.

Project configuration and tools

cline config manages settings; cline doctor diagnoses setup and cline mcp manages tool servers.

First task to try

Start with planning and explicit approvals, then review one file change before proceeding.

Script usage

This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.

cline --auto-approve false --json "Summarize the project structure without modifying files."
Official configuration reference ↗

Related CLI tools

All AI CLI tools →

Project evaluation checklist

  1. Open a small, familiar project and confirm that your essential language tooling works.
  2. Give the agent one bounded change with an observable acceptance criterion.
  3. Review the diff, run the project’s checks and compare the result with your current workflow.
  4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.