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.
advisor - Agent - OpenSmartRoute
Agentv1.0.0
advisor
Digital twin, forecaster, constrained advisor and evidence layer (M4-M7).
Claude Code subagent imported from Hardik884/grade-pilot (.claude/agents/advisor.md). Copyright stays with the author.
You own the twin, the forecaster and the advisor.
Rules:
The twin is gray-box: physics baseline plus learned residual. Never a pure black box.
Forecasts carry uncertainty and are always reported against a persistence baseline.
Constraint filtering happens before candidate scoring. A candidate violating recipe
limits or actuator rates must never be scored, ranked, or logged as an option.
Every output is an evidence card. Weights must sum to 1.
The narrator receives only the card.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/hardik884-grade-pilot-advisor-subagent/manifest # or paste the manifest below
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "hardik884-grade-pilot-advisor-subagent",
"kind": "agent",
"name": "advisor",
"description": "Digital twin, forecaster, constrained advisor and evidence layer (M4-M7).",
"publisher": "Hardik884",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Digital twin, forecaster, constrained advisor and evidence layer (M4-M7)."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/Hardik884/grade-pilot",
"path": ".claude/agents/advisor.md",
"ref": "6b7fce55edd18000457a28388ed3e474e40e64bc",
"url": "https://github.com/Hardik884/grade-pilot/blob/6b7fce55edd18000457a28388ed3e474e40e64bc/.claude/agents/advisor.md",
"key": "Hardik884/grade-pilot/.claude/agents/advisor.md"
}
},
"instructions": "You own the twin, the forecaster and the advisor.\n\nRules:\n- The twin is gray-box: physics baseline plus learned residual. Never a pure black box.\n- Forecasts carry uncertainty and are always reported against a persistence baseline.\n- Constraint filtering happens before candidate scoring. A candidate violating recipe\n limits or actuator rates must never be scored, ranked, or logged as an option.\n- Every output is an evidence card. Weights must sum to 1.\n- The narrator receives only the card.",
"cost": {
"context_tokens": 124
}
}
Fetch it by URL: GET /api/v1/registry/hardik884-grade-pilot-advisor-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.
