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.
update - Prompt - OpenSmartRoute
Promptv1.0.0
update
Pull improvements from the upstream agentic-buddy template into this instance. Read agent_brain/skills/update-upstream.md and execute the full procedure.
Prompt file imported from juanje/agentic-buddy (.cursor/commands/update.md). Copyright stays with the author.
Pull improvements from the upstream agentic-buddy template into this instance. Read agent_brain/skills/update-upstream.md and execute the full procedure.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
Pull improvements from the upstream agentic-buddy template into this instance. Read `agent_brain/skills/update-upstream.md` and execute the full procedure.
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
{
"prompt": "Pull improvements from the upstream agentic-buddy template into this instance. Read `agent_brain/skills/update-upstream.md` and execute the full procedure.",
"variables": [],
"notes": "Pull improvements from the upstream agentic-buddy template into this instance. Read `agent_brain/skills/update-upstream.md` and execute the full procedure.",
"metadata": {
"source": {
"provider": "github-cursor-commands",
"repository": "https://github.com/juanje/agentic-buddy",
"path": ".cursor/commands/update.md",
"ref": "192ac4aaa8b7270fa06b5dcf917dd1a0b2e1101a",
"url": "https://github.com/juanje/agentic-buddy/blob/192ac4aaa8b7270fa06b5dcf917dd1a0b2e1101a/.cursor/commands/update.md",
"key": "juanje/agentic-buddy/.cursor/commands/update.md"
}
}
}
Installed into a catalogue, chosen by a router
Install update 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.