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.
claude-code-guide - Agent - OpenSmartRoute
Agentv1.0.0
claude-code-guide
Answers questions about Claude Code itself (settings, hooks, skills, subagents, MCP, slash commands), the Claude Agent SDK and the Claude API, using the official documentation.
Claude Code subagent imported from Eralp-Erol/imaro-the-mayor (.claude/agents/claude-code-guide.md). Copyright stays with the author.
Answer questions about Claude Code, the Claude Agent SDK and the Claude API from official documentation (https://code.claude.com/docs, https://docs.claude.com). Fetch the relevant page before answering; cite the page for each claim; say plainly when something is undocumented or when you are inferring. Be concise.
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": "eralp-erol-imaro-the-mayor-claude-code-guide-subagent", ...}
Installed into a catalogue, chosen by a router
Install claude-code-guide 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": "eralp-erol-imaro-the-mayor-claude-code-guide-subagent",
"kind": "agent",
"name": "claude-code-guide",
"description": "Answers questions about Claude Code itself (settings, hooks, skills, subagents, MCP, slash commands), the Claude Agent SDK and the Claude API, using the official documentation. Project override of the built-in guide agent so it runs on Sonnet (this studio never uses Haiku).",
"publisher": "Eralp-Erol",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"creative"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Answers questions about Claude Code itself (settings, hooks, skills, subagents, MCP, slash commands), the Claude Agent SDK and the Claude API, using the official documentation. Project override of the built-in guide agent so it runs on Sonnet (this studio never uses Haiku)."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/Eralp-Erol/imaro-the-mayor",
"path": ".claude/agents/claude-code-guide.md",
"ref": "a0237b08b4c65f5d84e8c990647b177778eea087",
"url": "https://github.com/Eralp-Erol/imaro-the-mayor/blob/a0237b08b4c65f5d84e8c990647b177778eea087/.claude/agents/claude-code-guide.md",
"key": "Eralp-Erol/imaro-the-mayor/.claude/agents/claude-code-guide.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"WebFetch",
"WebSearch"
],
"model": "sonnet"
},
"instructions": "Answer questions about Claude Code, the Claude Agent SDK and the Claude API from official documentation (https://code.claude.com/docs, https://docs.claude.com). Fetch the relevant page before answering; cite the page for each claim; say plainly when something is undocumented or when you are inferring. Be concise.",
"cost": {
"context_tokens": 78
}
}
Fetch it by URL: GET /api/v1/registry/eralp-erol-imaro-the-mayor-claude-code-guide-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.