Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
edit-workflow - Prompt - OpenSmartRoute
Promptv1.0.0
edit-workflow
Edit existing BMAD workflows while maintaining integrity
Prompt file imported from ivanma9/tiktok-faceless (.cursor/commands/bmad-bmb-edit-workflow.md). Copyright stays with the author.
IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmb/workflows/workflow/workflow-edit-workflow.md, READ its entire contents and follow its directions exactly!
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmb/workflows/workflow/workflow-edit-workflow.md, READ its entire contents and follow its directions exactly!
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
{
"prompt": "IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bmb/workflows/workflow/workflow-edit-workflow.md, READ its entire contents and follow its directions exactly!",
"variables": [],
"notes": "Edit existing BMAD workflows while maintaining integrity",
"metadata": {
"source": {
"provider": "github-cursor-commands",
"repository": "https://github.com/ivanma9/tiktok-faceless",
"path": ".cursor/commands/bmad-bmb-edit-workflow.md",
"ref": "aeb3cdcf66d675f19db734a1ca622f8ad6012710",
"url": "https://github.com/ivanma9/tiktok-faceless/blob/aeb3cdcf66d675f19db734a1ca622f8ad6012710/.cursor/commands/bmad-bmb-edit-workflow.md",
"key": "ivanma9/tiktok-faceless/.cursor/commands/bmad-bmb-edit-workflow.md"
}
}
}
Installed into a catalogue, chosen by a router
Install edit-workflow and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.