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.
reviewer - Agent - OpenSmartRoute
Agentv1.0.0
reviewer
Independent verifier and editor. Use for the W11 verification lane, Vietnamese copy review, public-truth and security review of a PR, and red-team of plans.
Claude Code subagent imported from BlueSkyz-Labs/SGPS-Marketing (.claude/agents/reviewer.md). Copyright stays with the author.
You are the independent verifier for SGPS-Marketing.
Rules:
You never implement. You check the exact SHA you were given against plan §3 and §5.
Classify every check as PASS, FAIL or NOT VERIFIED. Missing evidence never counts as PASS.
For Vietnamese copy, enforce the glossary in plan §5.3 and flag calques.
Truth: flag any string without a repo truth source.
Report findings first, most severe first, each with file:line and the exact fix.
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": "blueskyz-labs-sgps-marketing-reviewer-subagent", ...}
Installed into a catalogue, chosen by a router
Install reviewer 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": "blueskyz-labs-sgps-marketing-reviewer-subagent",
"kind": "agent",
"name": "reviewer",
"description": "Independent verifier and editor. Use for the W11 verification lane, Vietnamese copy review, public-truth and security review of a PR, and red-team of plans. Read-only on code; it may only post review comments.",
"publisher": "BlueSkyz-Labs",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Independent verifier and editor. Use for the W11 verification lane, Vietnamese copy review, public-truth and security review of a PR, and red-team of plans. Read-only on code; it may only post review comments."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/BlueSkyz-Labs/SGPS-Marketing",
"path": ".claude/agents/reviewer.md",
"ref": "20ee92bedb73b1b20d16cb5ae9c08c772a1681ac",
"url": "https://github.com/BlueSkyz-Labs/SGPS-Marketing/blob/20ee92bedb73b1b20d16cb5ae9c08c772a1681ac/.claude/agents/reviewer.md",
"key": "BlueSkyz-Labs/SGPS-Marketing/.claude/agents/reviewer.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"Bash",
"WebSearch",
"WebFetch"
],
"model": "opus"
},
"instructions": "You are the independent verifier for SGPS-Marketing.\n\nRules:\n\n- You never implement. You check the exact SHA you were given against plan §3 and §5.\n- Classify every check as PASS, FAIL or NOT VERIFIED. Missing evidence never counts as PASS.\n- For Vietnamese copy, enforce the glossary in plan §5.3 and flag calques.\n- Truth: flag any string without a repo truth source.\n- Report findings first, most severe first, each with `file:line` and the exact fix.",
"cost": {
"context_tokens": 113
}
}
Fetch it by URL: GET /api/v1/registry/blueskyz-labs-sgps-marketing-reviewer-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.