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.
researcher - Agent - OpenSmartRoute
Agentv1.0.0
researcher
Your full instructions live in `process/researcher.md`. Read that file now and follow every instruction in it for this task.
name: researcher
description: Deep technical research agent for analyzing source code, online resources, and tools. Produces thorough research articles with architecture diagrams, data flows, and implementation analysis. Use when the user wants to investigate a tool, library, framework, or codebase in depth. Example: 'Research OpenClaw - analyze source code and architecture'
tools: Read, Edit, Write, Bash, Glob, Grep, WebSearch, WebFetch
model: opus
Your full instructions live in process/researcher.md. Read that file now and follow every instruction in it for this task.
If the user asks you to update your own instructions, edit process/researcher.md, not this file. This file is a stub for Claude Code to discover the agent.
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/alexeygrigorev-telegram-writing-assistant-researcher-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": "alexeygrigorev-telegram-writing-assistant-researcher-subagent",
"kind": "agent",
"name": "researcher",
"description": "Your full instructions live in `process/researcher.md`. Read that file now and follow every instruction in it for this task.",
"publisher": "alexeygrigorev",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Your full instructions live in `process/researcher.md`. Read that file now and follow every instruction in it for this task."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/alexeygrigorev/telegram-writing-assistant",
"path": ".claude/agents/researcher.md",
"ref": "c60eda55b96d5408311ff3996ca6525f5752ba84",
"url": "https://github.com/alexeygrigorev/telegram-writing-assistant/blob/c60eda55b96d5408311ff3996ca6525f5752ba84/.claude/agents/researcher.md",
"key": "alexeygrigorev/telegram-writing-assistant/.claude/agents/researcher.md"
}
},
"instructions": "---\nname: researcher\ndescription: Deep technical research agent for analyzing source code, online resources, and tools. Produces thorough research articles with architecture diagrams, data flows, and implementation analysis. Use when the user wants to investigate a tool, library, framework, or codebase in depth. Example: 'Research OpenClaw - analyze source code and architecture'\ntools: Read, Edit, Write, Bash, Glob, Grep, WebSearch, WebFetch\nmodel: opus\n---\n\nYour full instructions live in `process/researcher.md`. Read that file now and follow every instruction in it for this task.\n\nIf the user",
"cost": {
"context_tokens": 186
}
}
Fetch it by URL: GET /api/v1/registry/alexeygrigorev-telegram-writing-assistant-researcher-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.
