AI assistants

neetodesk setup writes NeetoDesk instructions into the place your assistant already reads, so it knows which commands exist and how to call them. Run it once per project or per machine, depending on the assistant.

This is not the same thing as the MCP server. setup teaches an assistant to run the CLI as a shell command using your CLI session. The MCP server exposes NeetoDesk as tools over HTTP, with its own connection and credentials. Use whichever suits the assistant in front of you, or both.

What each command writes

Command	Writes to	Scope
`neetodesk setup claude`	`~/.config/neetodesk/claude-plugin`	Machine
`neetodesk setup cursor`	`.cursor/rules/neetodesk.mdc`	Project
`neetodesk setup windsurf`	`.windsurf/rules/neetodesk.md`	Project
`neetodesk setup copilot`	`.github/copilot-instructions.md`	Project
`neetodesk setup gemini`	`GEMINI.md`	Project
`neetodesk setup codex`	`AGENTS.md`	Project

The project-scoped commands write into the working directory, so run them from the repository root. Files that hold other instructions are not overwritten: Copilot, Gemini and Codex get a ## NeetoDesk CLI section appended, and re-running replaces just that section. Cursor and Windsurf rule files are left alone if they already exist, and the command says so rather than clobbering your edits.

Claude Code

Claude Code installs plugins through interactive slash commands, so setup claude extracts the plugin and then tells you the two commands to run:

neetodesk setup claude

NeetoDesk plugin extracted to /Users/you/.config/neetodesk/claude-plugin

To finish installation, open Claude Code and run these slash commands:
  /plugin marketplace add /Users/you/.config/neetodesk/claude-plugin
  /plugin install neetodesk@neetodesk

The command fails if ~/.claude/ does not exist, which means Claude Code has not been run on this machine yet.

Everything else

neetodesk setup cursor
neetodesk setup windsurf
neetodesk setup copilot
neetodesk setup gemini
neetodesk setup codex

Restart the assistant, or start a new conversation, so it picks the instructions up.

Output for agents

Assistants read command output as text, and JSON spends a lot of tokens on punctuation. --toon emits the same data in a more compact encoding:

neetodesk tickets list --toon

See Output formats for the other modes.

Getting Started

Commands

What each command writes

Claude Code

Everything else

Output for agents

​What each command writes

​Claude Code

​Everything else

​Output for agents

What each command writes

Claude Code

Everything else

Output for agents