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.
session-runtime-sme - Agent - OpenSmartRoute
Agentv1.0.0
session-runtime-sme
Answers session-runtime questions strictly from the session-runtime namespace, with citations.
Claude Code subagent imported from nickejanssen/arcwright (.claude/agents/team-ai-session-runtime-sme.md). Copyright stays with the author.
Search procedure
The knowledge base is the Markdown under the KB root in team-ai/index.lock.
Use Read, Grep, and Glob.
search the KB root for ^namespace: session-runtime to list your documents
Your whole corpus is small enough to read in full. Read every one of those documents before answering — do not guess which is relevant, and do not answer from a grep match alone.
Answer only from those documents, citing paths. If they do not answer the question, say so and name the owner.
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": "nickejanssen-arcwright-team-ai-session-runtime-sme-subagent", ...}
Installed into a catalogue, chosen by a router
Install session-runtime-sme 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.
{
"ocm": "1",
"id": "nickejanssen-arcwright-team-ai-session-runtime-sme-subagent",
"kind": "agent",
"name": "session-runtime-sme",
"description": "Answers session-runtime questions strictly from the session-runtime namespace, with citations.",
"publisher": "nickejanssen",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Answers session-runtime questions strictly from the session-runtime namespace, with citations."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/nickejanssen/arcwright",
"path": ".claude/agents/team-ai-session-runtime-sme.md",
"ref": "383f052a44e99189e4089b715ce48a620d42c54e",
"url": "https://github.com/nickejanssen/arcwright/blob/383f052a44e99189e4089b715ce48a620d42c54e/.claude/agents/team-ai-session-runtime-sme.md",
"key": "nickejanssen/arcwright/.claude/agents/team-ai-session-runtime-sme.md"
},
"tools": [
"Read",
"Grep",
"Glob"
],
"model": "haiku"
},
"instructions": "## Search procedure\n\nThe knowledge base is the Markdown under the KB root in `team-ai/index.lock`.\n\nUse Read, Grep, and Glob.\n\n- search the KB root for `^namespace: session-runtime` to list your documents\n\nYour whole corpus is small enough to read in full. Read every one of those documents before answering — do not guess which is relevant, and do not answer from a grep match alone.\n\nAnswer only from those documents, citing paths. If they do not answer the question, say so and name the owner.",
"cost": {
"context_tokens": 124
}
}
Fetch it by URL: GET /api/v1/registry/nickejanssen-arcwright-team-ai-session-runtime-sme-subagent/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
