Best use case
ecomode is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Token-efficient model routing modifier
Teams using ecomode should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ecomode/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ecomode Compares
| Feature / Agent | ecomode | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Token-efficient model routing modifier
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
# 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 `ralph` for "don't stop until done"
- **Parallel Execution**: Use `ultrawork` for 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 |
| UPGRADE | Escalate to STANDARD when LOW tier fails or task requires multi-file reasoning |
| AVOID | THOROUGH tier - only for planning/critique if essential |
## Agent Selection in Ecomode
**FIRST ACTION:** Before delegating any work, read the agent reference file:
```
Read file: docs/shared/agent-tiers.md
```
This provides the complete agent tier matrix, MCP tool assignments, and selection guidance.
**Ecomode preference order:**
```
// PREFERRED - Use for most tasks
delegate(role="executor", tier="LOW", task="...")
delegate(role="explore", tier="LOW", task="...")
delegate(role="architect", tier="LOW", task="...")
// FALLBACK - Only if LOW fails
delegate(role="executor", tier="STANDARD", task="...")
delegate(role="architect", tier="STANDARD", task="...")
// AVOID - Only for planning/critique if essential
delegate(role="planner", tier="THOROUGH", task="...")
```
## Delegation Enforcement
Ecomode maintains all delegation rules from core protocol with cost-optimized routing:
| Action | Delegate To | Model |
|--------|-------------|-------|
| Code changes | executor | LOW / STANDARD |
| Analysis | architect | LOW |
| Search | explore | LOW |
| Documentation | writer | LOW |
### Background Execution
Long-running commands (install, build, test) run in background. Maximum 20 concurrent.
## Token Savings Tips
1. **Batch similar tasks** to one agent instead of spawning many
2. **Use explore (LOW tier)** for file discovery, not architect
3. **Prefer LOW-tier executor routing** for simple changes - only upgrade if it fails
4. **Use writer (LOW tier)** for all documentation tasks
5. **Avoid THOROUGH-tier agents** unless the task genuinely requires deep reasoning
## Disabling Ecomode
Ecomode can be completely disabled via config. When disabled, all ecomode keywords are ignored.
Set in `~/.codex/.omx-config.json`:
```json
{
"ecomode": {
"enabled": false
}
}
```
## State Management
Use `omx_state` MCP tools for ecomode lifecycle state.
- **On activation**:
`state_write({mode: "ecomode", active: true})`
- **On deactivation/completion**:
`state_write({mode: "ecomode", active: false})`
- **On cancellation/cleanup**:
run `$cancel` (which should call `state_clear(mode="ecomode")`)Related Skills
worker
Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams
web-clone
URL-driven website cloning with visual + functional verification
visual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons
ultrawork
Parallel execution engine for high-throughput task completion
ultraqa
QA cycling workflow - test, verify, fix, repeat until goal met
trace
Show agent flow trace timeline and summary
team
N coordinated agents on shared task list using tmux-based orchestration
tdd
Test-Driven Development enforcement skill - write tests first, always
swarm
N coordinated agents on shared task list (compatibility facade over team)
skill
Manage local skills - list, add, remove, search, edit, setup wizard
ralplan
Alias for $plan --consensus
ralph
Self-referential loop until task completion with architect verification