Prioritize cheaper AI model tiers in routing workflows with configurable opt-outs and safety guards.
npx skills add https://github.com/pextacy/stellar --skill ecomode-pextacy
Please help me install this Agent Skill. Skill: ecomode Source: https://github.com/pextacy/stellar/tree/main/skills/ecomode Command: npx skills add https://github.com/pextacy/stellar --skill ecomode-pextacy
Token-efficient model routing reduces operational costs by prioritizing cheaper AI model tiers and escalating only when necessary.
Enable ecomode in your config to begin cost-aware, tiered model routing.
High-intent search queries and answers about installing and using this skill.
Tier-aware AI model routing reduces operational costs by prioritizing cheaper model tiers and escalating to higher tiers only when necessary, preserving essential performance while optimizing resource usage.
You can enable ecomode in your configuration to begin cost-aware, tiered model routing, applying tier-aware decision logic with configurable opt-out and safety guards to ensure essential performance.
Yes, you can use the safe opt-out and easy configuration features for scenarios requiring full fidelity or custom routing, bypassing the default cost-optimization logic.
The best way to optimize AI token costs is implementing tier-aware routing that prioritizes lower-cost models while maintaining core protocol safeguards and applying safety guards for essential performance.
You should not use cheaper model tiers when scenarios require full fidelity or custom routing, instead utilizing the safe opt-out configuration to bypass cost-optimization constraints.
kriscendobotRoutes AI agent tasks to appropriate model tiers with fallback logic.
Xza85hrfRoute tasks across Opus, Sonnet, Haiku, Ollama Cloud, and Ollama Local to minimize token costs.
RambleRainbowRoute LLM API tasks by complexity and track spend with immutable budget limits.
cescrafliCoordinate AI-driven engineering tasks with eval-first execution and cost-aware model routing.
