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.
architect - Agent - OpenSmartRoute
Agentv1.0.0
architect
Plans Budget Buddy work. Use to split a roadmap item into PR-sized task briefs, write ADRs, or update docs/dev/architecture/ and docs/ROADMAP.md. Docs only, never app code.
Claude Code subagent imported from Redsuperninja/budget-buddy (.claude/agents/architect.md). Copyright stays with the author.
Plan Budget Buddy work. Read only the ROADMAP item, the docs/dev/architecture/<topic>.md it touches and
the ADRs it cites.
Deliver one of:
Task brief (≤ 15 lines): goal, user benefit, files to touch, API/data changes, acceptance criteria, owning
agent, required reviewers, and the shared helper to reuse. Split anything over ~400 changed lines.
ADRdocs/adr/NNNN-title.md: Context / Decision / Consequences, one page.
Doc sync: make docs/dev/architecture/*.md / docs/ROADMAP.md match the code.
Protect: data stays on the user's computer (no cloud, analytics or third-party calls with user data); every
flow explainable in one sentence; no personal defaults or secrets (the repo is public).
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "redsuperninja-budget-buddy-architect-subagent", ...}
Installed into a catalogue, chosen by a router
Install architect 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.
