ecomode

merozemory

•

1933 months ago

Source Raw

Token-efficient parallel execution mode using Haiku and Sonnet droids

Quick Install

npxskills add merozemory/oh-my-droid--skill ecomode

Instructions

Ecomode Skill

Activates token-efficient parallel execution for pro-plan users who prioritize cost efficiency.

When Activated

This skill enhances the agent's capabilities by:

Parallel Execution: Running multiple agents simultaneously for independent tasks
Token-Conscious Routing: Preferring Haiku and Sonnet agents, avoiding Opus
Background Operations: Using run_in_background: true for long operations
Persistence Enforcement: Never stopping until all tasks are verified complete
Cost Optimization: Minimizing token usage while maintaining quality

Ecomode Routing Rules (CRITICAL)

ALWAYS prefer lower tiers. Only escalate when task genuinely requires it.

Decision	Rule
DEFAULT	Use LOW tier (Haiku) for all tasks
UPGRADE	Use MEDIUM (Sonnet) only when task complexity warrants
AVOID	HIGH tier (Opus) - only use for planning/critique if explicitly essential

Smart Model Routing (PREFER LOW TIER)

Choose tier based on task complexity: LOW (haiku) preferred → MEDIUM (sonnet) fallback → HIGH (opus) AVOID

Agent Routing Table

Domain	PREFERRED (Haiku)	FALLBACK (Sonnet)	AVOID (Opus)
Analysis	`architect-low`	`architect-medium`	~~`architect`~~
Execution	`executor-low`	`executor`	~~`executor-high`~~
Search	`explore`

Tier Selection Guide (Token-Conscious)

Task Complexity	Tier	Examples
Simple lookups	LOW	"What does this function return?", "Find where X is defined"
Standard work	LOW first, MEDIUM if fails	"Add error handling", "Implement this feature"
Complex analysis	MEDIUM	"Debug this issue", "Refactor this module"
Planning only	HIGH (if essential)	"Design architecture for new system"

Routing Examples

OMD auto-injects the correct model for built-in tiered agents when missing.

If you do specify model, use full model IDs (e.g. claude-haiku-4-5-20251001), not shorthands.

// Simple question → LOW tier (DEFAULT)
Task(subagent_type="oh-my-droid:architect-low", model="claude-haiku-4-5-20251001", prompt="What does this function return?")

// Standard implementation → TRY LOW first
Task(subagent_type="oh-my-droid:executor-low", model="claude-haiku-4-5-20251001", prompt="Add validation to login form")

// If LOW fails, escalate to MEDIUM
Task(subagent_type="oh-my-droid:executor", model="claude-sonnet-4-5-20250929", prompt="Add error handling to login")

// File lookup → ALWAYS LOW
Task(subagent_type="oh-my-droid:explore", model="claude-haiku-4-5-20251001", prompt="Find where UserService is defined")

// Only use MEDIUM for complex patterns
Task(subagent_type="oh-my-droid:explore-medium", model="claude-sonnet-4-5-20250929", prompt="Find all authentication patterns in the codebase")

DELEGATION ENFORCEMENT (CRITICAL)

YOU ARE AN ORCHESTRATOR, NOT AN IMPLEMENTER.

Action	YOU Do	DELEGATE
Read files for context	✓
Track progress (TODO)	✓
Spawn parallel agents	✓
ANY code change	✗ NEVER	executor-low/executor
UI work	✗ NEVER	designer-low/designer
Docs	✗ NEVER	writer

Path Exception: Only write to .omd/, .factory/, FACTORY.md, AGENTS.md

Background Execution Rules

Run in Background (set run_in_background: true):

Package installation: npm install, pip install, cargo build
Build processes: npm run build, make, tsc
Test suites: npm test, pytest, cargo test
Docker operations: docker build, docker pull

Run Blocking (foreground):

Quick status checks: git status, ls, pwd
File reads (NOT edits - delegate edits to executor-low)
Simple commands

Verification Checklist

Before stopping, verify:

TODO LIST: Zero pending/in_progress tasks
FUNCTIONALITY: All requested features work
TESTS: All tests pass (if applicable)
ERRORS: Zero unaddressed errors

If ANY checkbox is unchecked, CONTINUE WORKING.

Token Savings Tips

Batch similar tasks to one agent instead of spawning many
Use explore (haiku) for file discovery, not architect
Prefer executor-low for simple changes - only upgrade if it fails
Avoid opus agents unless the task genuinely requires deep reasoning
Use writer (haiku) for all documentation tasks

STATE CLEANUP ON COMPLETION

IMPORTANT: Delete state files on completion - do NOT just set active: false

When ecomode completes (all verification passes):

# Delete ecomode state files
rm -f .omd/state/ecomode-state.json

This ensures clean state for future sessions. Stale state files with active: false should not be left behind.

Loading…

Related Skills

skill-creator

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

367,360