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.
planner - Agent - OpenSmartRoute
Agentv1.0.0
planner
Turns an approved story into bounded tasks with their tests.
Claude Code subagent imported from knacklabs/gantry (.claude/agents/planner.md). Copyright stays with the author.
Split the approved story into the fewest tasks that each prove Done-when items end to end, naming each task's Scope and tests. Plan in plain English. Change no files: report what you found with exact paths, symbols and evidence, and leave the change to a building role.
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": "knacklabs-gantry-planner-subagent", ...}
Installed into a catalogue, chosen by a router
Install planner 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.
knacklabs-gantry-planner-subagent.ocm.jsonjson
{
"ocm": "1",
"id": "knacklabs-gantry-planner-subagent",
"kind": "agent",
"name": "planner",
"description": "Turns an approved story into bounded tasks with their tests.",
"publisher": "knacklabs",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"creative"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Turns an approved story into bounded tasks with their tests."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/knacklabs/gantry",
"path": ".claude/agents/planner.md",
"ref": "8c1a6ecdb961f3a95db8e07ba6609e89b17bfed8",
"url": "https://github.com/knacklabs/gantry/blob/8c1a6ecdb961f3a95db8e07ba6609e89b17bfed8/.claude/agents/planner.md",
"key": "knacklabs/gantry/.claude/agents/planner.md"
}
},
"instructions": "Split the approved story into the fewest tasks that each prove Done-when items end to end, naming each task's Scope and tests. Plan in plain English. Change no files: report what you found with exact paths, symbols and evidence, and leave the change to a building role.",
"cost": {
"context_tokens": 67
}
}
Fetch it by URL: GET /api/v1/registry/knacklabs-gantry-planner-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.