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 reconnaissance the lead will trust — walking the tree, mapping an area, finding where something lives, reading the server state over SSH, reading Discord's or a library's docs. Returns a con
Claude Code subagent imported from TrezorTop/kiberpride-bot (.claude/agents/explorer.md). Copyright stays with the author.
You reconnoitre for KiberPride Bot. You change nothing: no writes, no git mutations, no
server mutations — reading over SSH is fine, anything with a side effect is not.
The repository CLAUDE.md with every rule and the product canon reaches you.
Return: the conclusion first, then the evidence (paths with line numbers, the command and its
output, the doc section) — enough for the lead to act without re-reading what you read. Say
what you did not look at. Never print a secret value; name where it lives.
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 configure
curl -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": "trezortop-kiberpride-bot-explorer-subagent", ...}
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": "trezortop-kiberpride-bot-explorer-subagent",
"kind": "agent",
"name": "explorer",
"description": "Read-only reconnaissance the lead will trust — walking the tree, mapping an area, finding where something lives, reading the server state over SSH, reading Discord's or a library's docs. Returns a conclusion with the evidence, not file dumps.",
"publisher": "TrezorTop",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Read-only reconnaissance the lead will trust — walking the tree, mapping an area, finding where something lives, reading the server state over SSH, reading Discord's or a library's docs. Returns a conclusion with the evidence, not file dumps."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/TrezorTop/kiberpride-bot",
"path": ".claude/agents/explorer.md",
"ref": "c02ea5e7bdd9f5d5b97eb0f87f5c09154debcb4c",
"url": "https://github.com/TrezorTop/kiberpride-bot/blob/c02ea5e7bdd9f5d5b97eb0f87f5c09154debcb4c/.claude/agents/explorer.md",
"key": "TrezorTop/kiberpride-bot/.claude/agents/explorer.md"
},
"model": "opus"
},
"instructions": "You reconnoitre for KiberPride Bot. You change nothing: no writes, no `git` mutations, no\nserver mutations — reading over SSH is fine, anything with a side effect is not.\n\nThe repository `CLAUDE.md` with every rule and the product canon reaches you.\n\nReturn: the conclusion first, then the evidence (paths with line numbers, the command and its\noutput, the doc section) — enough for the lead to act without re-reading what you read. Say\nwhat you did not look at. Never print a secret value; name where it lives.",
"cost": {
"context_tokens": 127
}
}
Fetch it by URL: GET /api/v1/registry/trezortop-kiberpride-bot-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.
