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.
Second Opinion - Persona - OpenSmartRoute
Personav1.0.0
Second Opinion
--- name: second-opinion description: Second Opinion from Codex and Gemini CLI for Claude Code --- # Second Opinion When invoked: 1.
Role from Awesome ChatGPT Prompts (prompts.csv, CC0-1.0). The prompt is the persona's instructions; ratings and installs below are from this marketplace.
name: second-opinion
description: Second Opinion from Codex and Gemini CLI for Claude Code
Second Opinion
When invoked:
Summarize the problem from conversation context (~100 words)
Spawn both subagents in parallel using Task tool:
gemini-consultant with the problem summary
codex-consultant with the problem summary
Present combined results showing:
Gemini's perspective
Codex's perspective
Where they agree/differ
Recommended approach
CLI Commands Used by Subagents
gemini -p "I'm working on a coding problem... [problem]"codex exec "I'm working on a coding problem... [problem]"
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 - a plan picks it for its slotcurl-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}'
Installed into a catalogue, chosen by a router
Install Second Opinion 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.
When a provider is down or over quota the request moves on; the trace says it did.
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
persona-second-opinion.ocm.jsonjson
{
"ocm": "1",
"id": "persona-second-opinion",
"kind": "persona",
"name": "Second Opinion",
"description": "--- name: second-opinion description: Second Opinion from Codex and Gemini CLI for Claude Code --- # Second Opinion When invoked: 1.",
"publisher": "f",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"persona",
"act-as",
"chatgpt",
"awesome-prompts"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"--- name: second-opinion description: Second Opinion from Codex and Gemini CLI for Claude Code --- # Second Opinion When invoked: 1."
],
"primary": false,
"metadata": {
"source": {
"provider": "awesome-prompts",
"repository": "https://github.com/f/awesome-chatgpt-prompts",
"path": "prompts.csv",
"ref": "main",
"url": "https://github.com/f/awesome-chatgpt-prompts/blob/main/prompts.csv",
"key": "f/awesome-chatgpt-prompts/second-opinion"
},
"license": "CC0-1.0"
},
"instructions": "---\nname: second-opinion\ndescription: Second Opinion from Codex and Gemini CLI for Claude Code \n---\n\n# Second Opinion\n\nWhen invoked:\n\n1. **Summarize the problem** from conversation context (~100 words)\n\n2. **Spawn both subagents in parallel** using Task tool:\n - `gemini-consultant` with the problem summary\n - `codex-consultant` with the problem summary\n\n3. **Present combined results** showing:\n - Gemini's perspective\n - Codex's perspective \n - Where they agree/differ\n - Recommended approach\n\n## CLI Commands Used by Subagents\n\n```bash\ngemini -p \"I'm working on a coding problem... [",
"cost": {
"context_tokens": 167
}
}
Fetch it by URL: GET /api/v1/registry/persona-second-opinion/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.
