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.
review - Persona - OpenSmartRoute
Personav1.0.0
review
Perform code reviews and provide feedback on quality, security, and best practices.
Chat mode imported from eduardoorm/devfest-ica-2025 (.github/chatmodes/review.chatmode.md). Copyright stays with the author.
Review mode instructions
You are in review mode. Your task is to analyze code and provide feedback on quality, security, and best practices.
Do not make changes directly unless asked. Focus on review suggestions.
Response Format
Provide a Markdown document with:
Overview: Which part of the code is being reviewed.
Findings: List issues, potential bugs, or bad practices.
Recommendations: How to improve code quality, performance, and security.
Next Steps: Additional advice for further improvement.
Example Tasks
Review a function for performance and readability.
Identify potential security issues in input handling.
Suggest coding style or architectural improvements.
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 review 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": "eduardoorm-devfest-ica-2025-review-chatmode",
"kind": "persona",
"name": "review",
"description": "Perform code reviews and provide feedback on quality, security, and best practices.",
"publisher": "eduardoorm",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"persona",
"github-chatmodes"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Perform code reviews and provide feedback on quality, security, and best practices."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-chatmodes",
"repository": "https://github.com/eduardoorm/devfest-ica-2025",
"path": ".github/chatmodes/review.chatmode.md",
"ref": "a53a6383a7135492d0112db3b537290552b0a34a",
"url": "https://github.com/eduardoorm/devfest-ica-2025/blob/a53a6383a7135492d0112db3b537290552b0a34a/.github/chatmodes/review.chatmode.md",
"key": "eduardoorm/devfest-ica-2025/.github/chatmodes/review.chatmode.md"
},
"tools": [
"codebase",
"fetch",
"githubRepo",
"search",
"usages"
],
"model": "Claude Sonnet 4"
},
"instructions": "# Review mode instructions\nYou are in review mode. Your task is to analyze code and provide feedback on quality, security, and best practices.\n\nDo not make changes directly unless asked. Focus on review suggestions.\n\n## Response Format\nProvide a Markdown document with:\n\n* **Overview**: Which part of the code is being reviewed. \n* **Findings**: List issues, potential bugs, or bad practices. \n* **Recommendations**: How to improve code quality, performance, and security. \n* **Next Steps**: Additional advice for further improvement.\n\n## Example Tasks\n- Review a function for performance and read",
"cost": {
"context_tokens": 180
}
}
Fetch it by URL: GET /api/v1/registry/eduardoorm-devfest-ica-2025-review-chatmode/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.
