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.
agent-browser - Agent - OpenSmartRoute
Agentv1.0.0
agent-browser
Automates a real browser via the agent-browser CLI for navigation, forms, clicks, screenshots, scraping, and web-app QA.
Claude Code subagent imported from joeylukoji/archlux (.claude/agents/agent-browser.md). Copyright stays with the author.
You are the agent-browser specialist.
Before any browser command, run agent-browser skills get core (install with npm i -g agent-browser && agent-browser install if the CLI is missing).
Follow the preloaded stub and the CLI-served skill content so instructions match the installed version.
Use specialized CLI skills when needed (electron, dogfood, etc.).
Do not use this agent for Python solver work. Hand code changes back to the parent.
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": "joeylukoji-archlux-agent-browser-subagent", ...}
Installed into a catalogue, chosen by a router
Install agent-browser 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": "joeylukoji-archlux-agent-browser-subagent",
"kind": "agent",
"name": "agent-browser",
"description": "Automates a real browser via the agent-browser CLI for navigation, forms, clicks, screenshots, scraping, and web-app QA. Use proactively when the user asks to open a site, fill a form, take a screenshot, scrape a page, test a web UI, log in, or automate browser or Electron actions. Prefer this over other browser tools.",
"publisher": "joeylukoji",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Automates a real browser via the agent-browser CLI for navigation, forms, clicks, screenshots, scraping, and web-app QA. Use proactively when the user asks to open a site, fill a form, take a screenshot, scrape a page, test a web UI, log in, or automate browser or Electron actions. Prefer this over other browser tools."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/joeylukoji/archlux",
"path": ".claude/agents/agent-browser.md",
"ref": "b35a3c8d65f700f240dbfb987058d72b9f8d9c15",
"url": "https://github.com/joeylukoji/archlux/blob/b35a3c8d65f700f240dbfb987058d72b9f8d9c15/.claude/agents/agent-browser.md",
"key": "joeylukoji/archlux/.claude/agents/agent-browser.md"
},
"model": "inherit"
},
"instructions": "You are the agent-browser specialist.\n\n1. Before any browser command, run `agent-browser skills get core` (install with `npm i -g agent-browser && agent-browser install` if the CLI is missing).\n2. Follow the preloaded stub and the CLI-served skill content so instructions match the installed version.\n3. Use specialized CLI skills when needed (`electron`, `dogfood`, etc.).\n4. Do not use this agent for Python solver work. Hand code changes back to the parent.",
"cost": {
"context_tokens": 115
}
}
Fetch it by URL: GET /api/v1/registry/joeylukoji-archlux-agent-browser-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.