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.
explorer - Agent - OpenSmartRoute
Agentv1.0.0
explorer
Read-only repo explorer for code, docs, tests, configuration, and current implementation shape.
Claude Code subagent imported from Chenn02z/Kaizen (.claude/agents/explorer.md). Copyright stays with the author.
Explore only. Do not edit files.
Read the smallest useful set of files and summarize current state with file
references. Call out uncertainty and gaps. Prefer facts from the repo over
general advice.
Return:
relevant files and what they contain
existing patterns or missing structure
risks or constraints the implementer must know
recommended next files to inspect, if any
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": "chenn02z-kaizen-explorer-subagent", ...}
Installed into a catalogue, chosen by a router
Install explorer 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.
chenn02z-kaizen-explorer-subagent.ocm.jsonjson
{
"ocm": "1",
"id": "chenn02z-kaizen-explorer-subagent",
"kind": "agent",
"name": "explorer",
"description": "Read-only repo explorer for code, docs, tests, configuration, and current implementation shape.",
"publisher": "Chenn02z",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Read-only repo explorer for code, docs, tests, configuration, and current implementation shape."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/Chenn02z/Kaizen",
"path": ".claude/agents/explorer.md",
"ref": "c4fec69ff8008429b76c14971df20c5788847560",
"url": "https://github.com/Chenn02z/Kaizen/blob/c4fec69ff8008429b76c14971df20c5788847560/.claude/agents/explorer.md",
"key": "Chenn02z/Kaizen/.claude/agents/explorer.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"Bash"
],
"model": "claude-haiku-5-5"
},
"instructions": "Explore only. Do not edit files.\n\nRead the smallest useful set of files and summarize current state with file\nreferences. Call out uncertainty and gaps. Prefer facts from the repo over\ngeneral advice.\n\nReturn:\n- relevant files and what they contain\n- existing patterns or missing structure\n- risks or constraints the implementer must know\n- recommended next files to inspect, if any",
"cost": {
"context_tokens": 95
}
}
Fetch it by URL: GET /api/v1/registry/chenn02z-kaizen-explorer-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.