ecomode

Route tasks to cheaper model tiers with escalation thresholds and state hooks.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/shaun0927/codex-superskills --skill ecomode-shaun0927
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ecomode
Source: https://github.com/shaun0927/codex-superskills/tree/main/skills/ecomode
Command: npx skills add https://github.com/shaun0927/codex-superskills --skill ecomode-shaun0927

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Token-efficient model routing reduces operational costs by preferring cheaper AI tiers while maintaining result quality.

Core Features & Use Cases

  • Default-to-cheaper tiers: Start with low-cost models and escalate only when necessary.
  • Works with other eco modes: Can combine with eco Ralph, eco ultrawork, and eco autopilot for cost-aware orchestration.
  • Delegation rules and state management: Enforces routing policies and exposes state hooks for tracking progress.

Quick Start

Run ecomode with a target task to route to cheaper agents while preserving quality.

Frequently Asked Questions about ecomode

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

FAQPage Schema
How do I reduce token usage when running multi-file code analysis?

To reduce token usage during multi-file code analysis, you can route work to cheaper model tiers by default. This approach minimizes operational costs by escalating to higher tiers only when necessary thresholds are met.

What is token-efficient model routing and how does it work?

Token-efficient model routing is a mechanism that enforces delegation rules to start with low-cost models. It manages state hooks and escalation thresholds to ensure cost-aware orchestration while maintaining result quality.

Can I combine cost-aware routing with other eco modes for debugging tasks?

Yes, you can combine cost-aware routing with other eco modes like eco Ralph, eco ultrawork, and eco autopilot. This synergy allows for cost-efficient orchestration during debugging and multi-file reasoning.

When should I use cheaper model tiers for agent selection?

You should use cheaper model tiers for agent selection when cost constraints exist for tasks like code analysis or debugging. Defaulting to low tiers minimizes expenses while enforced routing policies maintain acceptable quality.

What are the limitations of defaulting to low-cost models for complex reasoning?

Defaulting to low-cost models for complex reasoning risks quality if escalation thresholds are improperly configured. The system relies on state management hooks to determine when delegation to higher tiers becomes necessary.