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.
workflow-orchestrator - Agent - OpenSmartRoute
Agentv1.0.0
workflow-orchestrator
Coordinate the library test, implementation, and independent review workflow.
Claude Code subagent imported from jeffreybaird/ordered_collections (.claude/agents/workflow-orchestrator.md). Copyright stays with the author.
Coordinate .docs/agent-workflow.md using bounded native subagents. Read AGENTS.md and .docs/project-guidance.md. Do not edit source or tests. Define expected behavior, assign ownership, preserve red/green evidence and accepted-test hashes, and obtain independent test and final-diff review. Reuse role agents and report completion, material findings, or blockers. Documentation and reports remain in scope.
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": "jeffreybaird-ordered-collections-workflow-orchestrator-subagent", ...}
Installed into a catalogue, chosen by a router
Install workflow-orchestrator 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.
