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.
persona - Agent - OpenSmartRoute
Agentv1.0.0
persona
Use this agent when AutoDesign needs a quick, cheap reaction to a candidate from a specific user persona — first impression, task readiness, gut-feel friction.
Claude Code subagent imported from MaromSv/AutoDesign (.claude/agents/persona.md). Copyright stays with the author.
TODO: persona system prompt
Placeholder body. The real prompt will: (1) take a persona description plus
one frame, (2) emit a short first-impression reaction in character (under
60 words), (3) flag any deal-breakers as a json field. Cheap model on purpose
— this signal runs often.
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": "maromsv-autodesign-persona-subagent", ...}
Installed into a catalogue, chosen by a router
Install persona 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.
When a provider is down or over quota the request moves on; the trace says it did.
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
maromsv-autodesign-persona-subagent.ocm.jsonjson
{
"ocm": "1",
"id": "maromsv-autodesign-persona-subagent",
"kind": "agent",
"name": "persona",
"description": "Use this agent when AutoDesign needs a quick, cheap reaction to a candidate from a specific user persona — first impression, task readiness, gut-feel friction.",
"publisher": "MaromSv",
"version": "1.0.0",
"capabilities": {
"domains": [
"creative"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Use this agent when AutoDesign needs a quick, cheap reaction to a candidate from a specific user persona — first impression, task readiness, gut-feel friction."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/MaromSv/AutoDesign",
"path": ".claude/agents/persona.md",
"ref": "4259abcfd4f506e11a1fad7048e8252c8dc5d53b",
"url": "https://github.com/MaromSv/AutoDesign/blob/4259abcfd4f506e11a1fad7048e8252c8dc5d53b/.claude/agents/persona.md",
"key": "MaromSv/AutoDesign/.claude/agents/persona.md"
},
"tools": [
"Read"
],
"model": "haiku"
},
"instructions": "# TODO: persona system prompt\n\nPlaceholder body. The real prompt will: (1) take a persona description plus\none frame, (2) emit a short first-impression reaction in character (under\n60 words), (3) flag any deal-breakers as a json field. Cheap model on purpose\n— this signal runs often.",
"cost": {
"context_tokens": 71
}
}
Fetch it by URL: GET /api/v1/registry/maromsv-autodesign-persona-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.