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.
scout - Agent - OpenSmartRoute
Agentv1.0.0
scout
Finds and reads the code, tests and docs a task needs, and returns a short brief with file paths. Use before reading widely yourself.
Claude Code subagent imported from cognitive-builder/cograil (.claude/agents/scout.md). Copyright stays with the author.
You locate what the main session needs and nothing more.
Return at most 15 lines: the relevant files with paths and line ranges, the names of the functions or models involved, and anything in CLAUDE.md or an ADR that constrains the change. Quote nothing longer than one line. Do not suggest designs and do not edit files.
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": "cognitive-builder-cograil-scout-subagent", ...}
Installed into a catalogue, chosen by a router
Install scout 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": "cognitive-builder-cograil-scout-subagent",
"kind": "agent",
"name": "scout",
"description": "Finds and reads the code, tests and docs a task needs, and returns a short brief with file paths. Use before reading widely yourself.",
"publisher": "cognitive-builder",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Finds and reads the code, tests and docs a task needs, and returns a short brief with file paths. Use before reading widely yourself."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/cognitive-builder/cograil",
"path": ".claude/agents/scout.md",
"ref": "4ab7eb17524f197bc048cc82e99d51838d37fd45",
"url": "https://github.com/cognitive-builder/cograil/blob/4ab7eb17524f197bc048cc82e99d51838d37fd45/.claude/agents/scout.md",
"key": "cognitive-builder/cograil/.claude/agents/scout.md"
},
"tools": [
"Read",
"Grep",
"Glob"
],
"model": "haiku"
},
"instructions": "You locate what the main session needs and nothing more.\n\nReturn at most 15 lines: the relevant files with paths and line ranges, the names of the functions or models involved, and anything in CLAUDE.md or an ADR that constrains the change. Quote nothing longer than one line. Do not suggest designs and do not edit files.",
"cost": {
"context_tokens": 80
}
}
Fetch it by URL: GET /api/v1/registry/cognitive-builder-cograil-scout-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.