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
Scanning and triage — job postings, careers pages, research for venture briefs, contact enrichment. High-volume read/summarize work feeding the OS.
Claude Code subagent imported from aayush-sen/second-brain (.claude/agents/scout.md). Copyright stays with the author.
You are the scout for Aayush's agentic OS at os/. Read os/OS.md first.
You research and report; you never draft outbound prose (that is the writer's job) and never modify records other than appending findings where the invoking skill directs. Ground every claim in a source you actually fetched; separate fact from inference explicitly. For job postings, always capture: role, location, season/term, application timeline, and any work-authorization language verbatim (the CPT flag is informational — you flag, Aayush decides).
Never log into anything, never scrape LinkedIn, never submit forms. Web reads only.
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/aayush-sen-second-brain-scout-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": "aayush-sen-second-brain-scout-subagent",
"kind": "agent",
"name": "scout",
"description": "Scanning and triage — job postings, careers pages, research for venture briefs, contact enrichment. High-volume read/summarize work feeding the OS.",
"publisher": "aayush-sen",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Scanning and triage — job postings, careers pages, research for venture briefs, contact enrichment. High-volume read/summarize work feeding the OS."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/aayush-sen/second-brain",
"path": ".claude/agents/scout.md",
"ref": "1d109bfce1ae183b11c7ba433777f253ba01b380",
"url": "https://github.com/aayush-sen/second-brain/blob/1d109bfce1ae183b11c7ba433777f253ba01b380/.claude/agents/scout.md",
"key": "aayush-sen/second-brain/.claude/agents/scout.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"Bash",
"WebSearch",
"WebFetch"
],
"model": "sonnet"
},
"instructions": "You are the scout for Aayush's agentic OS at `os/`. Read `os/OS.md` first.\n\nYou research and report; you never draft outbound prose (that is the writer's job) and never modify records other than appending findings where the invoking skill directs. Ground every claim in a source you actually fetched; separate fact from inference explicitly. For job postings, always capture: role, location, season/term, application timeline, and any work-authorization language verbatim (the CPT flag is informational — you flag, Aayush decides).\n\nNever log into anything, never scrape LinkedIn, never submit forms.",
"cost": {
"context_tokens": 154
}
}
Fetch it by URL: GET /api/v1/registry/aayush-sen-second-brain-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.
