# somm

> somm — r0lm0-somm. Use this tool when you need to optimize AI model selection for your agents, as it recommends the best model per role based on your existing subscriptions, considering factors like benchmarks and pricing. It solves the problem of manually evaluating and choosing suitable AI models, saving time and resources. By integrating with git, somm provides a streamlined interface for inputting agent roles and outputting tailored model recommendations.

Canonical page: https://skillsregistry.net/skills/r0lm0-somm  
JSON: https://api.skillsregistry.net/v1/skills/r0lm0-somm

## Description

MCP server that recommends the best AI model per agent role — from the subscriptions you actually have. Benchmarks, pricing, and the why

## Trust

- **Trust score (0–1):** 0.56
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/R0LM0/somm)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "r0lm0-somm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/r0lm0-somm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/r0lm0-somm/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt