ecomode

Route Claude Code tasks to cheaper model tiers with escalation rules.

Updated Feb 15, 2026
One-click install
npx skills add https://github.com/leejaedus/pepcode --skill ecomode-leejaedus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ecomode
Source: https://github.com/leejaedus/pepcode/tree/main/skills/ecomode
Command: npx skills add https://github.com/leejaedus/pepcode --skill ecomode-leejaedus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Token-efficient model routing modifier that reduces token usage by preferring cheaper model tiers while preserving task fidelity.

Core Features & Use Cases

  • Cost-aware tier routing: Start with cheaper model tiers and escalate only when essential.
  • Modifier integration: Works with existing modes (ralph, ultrawork, autopilot) as a non-persistent routing layer.
  • Delegation guidance: Explicit rules for agent selection and task delegation to minimize cost.

Quick Start

Apply the ecomode modifier to your Claude Code task to route to cheaper model tiers first and escalate only when necessary.

Frequently Asked Questions about ecomode

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

FAQPage Schema
How do I reduce token costs in Claude Code multi-agent workflows?

Apply a non-persistent routing modifier to your Claude Code task that enforces tier-based decision rules, starting with cheaper model tiers and escalating only when essential to preserve task fidelity.

Can I use cost-optimization routing with existing Claude Code modes like autopilot?

Cost-optimization routing works with existing modes like ralph, ultrawork, and autopilot as a non-persistent routing layer, integrating seamlessly without affecting persistence or core delegation logic.

How does model tier selection work for multi-agent task delegation?

Model tier selection for multi-agent task delegation works through explicit routing rules that guide agent selection, preferring cheaper tiers first and providing a clear escalation path only when task complexity demands it.

Does applying a routing modifier affect my Claude Code session persistence?

Applying a routing modifier does not affect session persistence or core delegation logic, functioning strictly as a non-persistent layer that routes tasks to cheaper model tiers without altering underlying state.

When should I escalate tasks to more expensive model tiers during cross-file reasoning?

Escalate tasks to more expensive model tiers during cross-file reasoning only when the initial cheaper tier cannot preserve task fidelity, utilizing the clear escalation path defined by the routing rules.