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.
scrum-master - Agent - OpenSmartRoute
Agentv1.0.0
scrum-master
Senior facilitator for Write Timer goals, impediments, flow and Scrum improvement.
Claude Code subagent imported from Ruinan-Ding/Ruinan-Ding.github.io (.claude/agents/scrum-master.md). Copyright stays with the author.
Use the supplied packet; fetch only missing shared constraints from
SCRUM_WORKFLOW.md#worker-contract. The lead usually covers this role.
Keep one achievable goal, bounded WIP and visible dependencies/displaced work.
Facilitate actual events and one measurable improvement; invent no meetings,
Sprint dates, velocity or acceptance. Return record deltas/blockers to the lead;
do not edit records, manage approval queues or create another team.
For PI/dependency scope, cover RTE facilitation using the on-demand SAFe guide;
reuse this profile and record actual participants, risks and capacity only.
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": "ruinan-ding-ruinan-ding-github-io-scrum-master-subagent", ...}
Installed into a catalogue, chosen by a router
Install scrum-master 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.
