#/commands or @ handles

1 messages · Page 1 of 1 (latest)

white goblet
#

I don't know if you are familiar with the BMAD method framework but I'd love to use it the same way it can be used with claude-code. So we need a way to directly reference agents / workflows. I like the claude-code cli approach. Can we make the experience more ergonomic for commands ?

glacial walrusBOT
#

Hi @white goblet. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Warp has made significant strides toward making referencing agents, workflows, and prompts as ergonomic as possible—similar to what you might be used to with Claude Code.

Direct referencing with @ and Slash Commands:

  • You can use the @ context menu to reference files, code symbols, Warp Drive objects (like workflows, notebooks, and rules), or even blocks from other sessions. For example, referencing a workflow in a prompt is as simple as typing @workflowName or selecting it from the menu. This inserts a reference token, and the agent automatically uses the contents as context for your task. This works both in natural language (Agent Mode) and classic terminal commands, making it very flexible and ergonomic for complex workflows or frameworks like BMAD Using @ to Add Context Referencing Warp Drive objects.

  • Slash Commands (/) are available in Agent Mode and Auto-Detection Mode. Typing / opens a menu where you can quickly run built-in actions or any saved prompts (including custom ones). This is similar to the CLI approach in Claude Code, letting you trigger workflows or agent actions without leaving the input field Slash Commands.

CLI Support:

  • Warp’s CLI also supports referencing Warp Drive objects directly in prompts, e.g.:
    warp agent run --prompt "Follow the instructions in <notebook:yourNotebookId>"
    This allows for programmatic and scriptable access to workflows and notebooks, much like the Claude Code CLI Referencing Warp Drive objects.
#

Recent Improvements:

  • Warp has added project-scoped rules (via WARP.md), slash commands, and improved the ergonomics of referencing and running workflows and prompts directly from the terminal, making the experience much closer to what you described Changelog 2025.08.13.

Summary:
You can reference agents, workflows, and prompts in Warp using both the @ context menu and / slash commands, and you can script these references via the CLI. This provides an ergonomic, flexible, and powerful way to use frameworks like BMAD or any custom workflow, similar to the Claude Code experience. If you have specific needs for even more ergonomic command-line usage, Warp is actively developing in this area and welcomes feedback.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@white goblet Kapa.ai is still learning and improving, please let me know how I did by reacting below.