ecomode
Token-efficient model routing modifier
Best for Cost-sensitive projectsWorks with GitHubLow risk
⌘source
- author
@Yeachan-Heo- language
- TypeScript
★24kstars
2kforks
Apr 19, 2026
✦overview.md
Key Features
- ·Overrides default model selection to prefer cheaper tiers
- ·Combines with execution modes like ralph and ultrawork
- ·Always prefers lower tiers, escalating only when necessary
Use Cases
- →Running a ralph loop with cheaper agents to reduce costs
- →Executing parallel tasks with ultrawork while optimizing for token efficiency
- →Performing autonomous tasks with autopilot under cost constraints
Best for
- ✓Cost-sensitive projects
- ✓High-volume task automation
Not ideal for
- !Tasks requiring maximum model capability
- !Situations where cost is not a constraint
FAQs
name
ecomode
description
Token-efficient model routing modifier
Ecomode Skill
Token-efficient model routing. This is a MODIFIER, not a standalone execution mode.
What Ecomode Does
Overrides default model selection to prefer cheaper tiers:
| Default Tier | Ecomode Override |
|---|---|
| THOROUGH | STANDARD, THOROUGH only if essential |
| STANDARD | LOW first, STANDARD if needed |
| LOW | LOW - no change |
What Ecomode Does NOT Do
- Persistence: Use
ralphfor "don't stop until done" - Parallel Execution: Use
ultraworkfor parallel agents - Delegation Enforcement: Always active via core orchestration
Combining Ecomode with Other Modes
Ecomode is a modifier that combines with execution modes:
| Combination | Effect |
|---|---|
eco ralph | Ralph loop with cheaper agents |
eco ultrawork | Parallel execution with cheaper agents |
eco autopilot | Full autonomous with cost optimization |
Ecomode Routing Rules
ALWAYS prefer lower tiers. Only escalate when task genuinely requires it.
| Decision | Rule |
|---|---|
| DEFAULT | Start with LOW tier for most tasks |
$install
1-click copynpx skills add Yeachan-Heo/oh-my-codex --skill ecomodeSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
1/ 5
poorThe SKILL.md content is hard to understand and quite ambiguous.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
1/ 5
not actionableThe SKILL.md is hard to act on; an agent would not know what to do.