Route AI model calls to cheaper tiers to minimize token usage.
npx skills add https://github.com/Tienching/oh-my-codebuddy --skill ecomode-tienching
Please help me install this Agent Skill. Skill: ecomode Source: https://github.com/Tienching/oh-my-codebuddy/tree/main/skills/ecomode Command: npx skills add https://github.com/Tienching/oh-my-codebuddy --skill ecomode-tienching
Token-efficient model routing modifier for cost-conscious AI orchestration.
Apply the ecomode modifier by prefixing commands with eco, for example eco ralph to run a low-cost Ralph loop.
High-intent search queries and answers about installing and using this skill.
You can optimize AI token usage by applying a model routing modifier that overrides default selection, preferring cheaper model tiers like STANDARD or LOW across delegation modes to minimize costs.
Cost-aware model routing is a technique that redirects AI model calls to cheaper execution tiers, downgrading tasks from THOROUGH to STANDARD or LOW whenever full processing power is not essential.
Yes, you can combine cost optimization with existing execution modes by prefixing commands, creating hybrid workflows like eco autopilot or eco ralph that balance operational costs with delegation behaviors.
Apply cheaper model tiers for background AI tasks by prefixing your commands with eco, which triggers state management rules that safely route operations to low-cost models without interrupting execution.
You should avoid lower model tiers when tasks require deep reasoning or high accuracy, as downgrading from THOROUGH to STANDARD or LOW prioritizes token efficiency over comprehensive processing capabilities.
planetaryescapeRoute user messages to optimal AI models via task classification and cost-aware tier selection.
suhwanOrchestrate Haiku and Sonnet agents for parallel, token-efficient task execution.
Yeachan-HeoRoute Claude Code requests to cheaper model tiers and escalate only when necessary.
xxihDiscover, select, and run multiple AI agents in parallel with aggregated results.
