mdes-ollama

Select token-safe AI models by testing the mdes.ollama endpoint with fallback.

1|Updated May 24, 2026
One-click install
npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill mdes-ollama
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mdes-ollama
Source: https://github.com/tinner-deinno/innova-skills-lib/tree/main/core/mdes-ollama
Command: npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill mdes-ollama

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The mdes-ollama skill solves the problem of unreliable AI model availability by automatically testing models on the MDES Ollama endpoint and selecting a working option with safe fallbacks.

Core Features & Use Cases

  • Central Model Orchestration: Runs a full health-check and routing flow so other skills can reliably obtain a working model.
  • Automatic Fallback Chain: Falls back from mdes.ollama models to codex, GPT Pro, and GitHub Copilot when Ollama models fail.
  • Token Usage Tracking & Guardrails: Monitors input/output tokens, computes usage %, and blocks models when usage exceeds critical thresholds.
  • Auto-Dev Loop Support: Enables automated testing and periodic health checks to keep the model pool ready for development workflows.

Use case example: When a multi-agent workflow starts (e.g., /nemotron or /gang), mdes-ollama ensures the best available model is selected based on success rate and token usage, then hands off execution to the chosen runtime.

Quick Start

Ask an agent to run: start model orchestration and pick the best working MDES Ollama model with fallback by issuing the command "/mdes-ollama".

Frequently Asked Questions about mdes-ollama

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does model orchestration handle Ollama endpoint failures?

Model orchestration handles Ollama endpoint failures by running automated health checks and automatically falling back to codex, GPT Pro, or GitHub Copilot to ensure reliable execution.

How do I set up an automatic fallback chain for multi-agent workflows?

Initiate the fallback chain by running an agent command to start model orchestration, which tests endpoint availability and selects the best working model with safe fallbacks for multi-agent workflows.

Why does token tracking block AI models during execution?

Token tracking blocks AI models during execution when usage percentages exceed critical thresholds, implementing necessary guardrails to prevent overconsumption and maintain development workflow stability.

Can I use this model health check with existing auto-dev loops?

Yes, you can use this model health check with existing auto-dev loops, as it supports periodic automated testing to keep the model pool ready and continuously validates integrated workflows.

What is the best way to select a token-safe AI model for orchestration commands?

The best way to select a token-safe AI model is using automated orchestration tests that compute usage percentages and success rates, routing commands to the safest available runtime.