pipeline

Orchestrate multi-stage OMX pipelines with state persistence and resume support.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/KYRIE66nb/codex-omx-public-config --skill pipeline-kyrie66nb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pipeline
Source: https://github.com/KYRIE66nb/codex-omx-public-config/tree/main/home/.agents/skills/pipeline
Command: npx skills add https://github.com/KYRIE66nb/codex-omx-public-config --skill pipeline-kyrie66nb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates and coordinates multi-stage OMX workflows, providing state persistence and resume support.

Core Features & Use Cases

  • Orchestrates the default pipeline sequence: ralplan -> team-exec -> ralph-verify, enabling consistent execution across runs.
  • Defines a reusable PipelineStage interface that stages implement to share context and results.
  • Supports state management and resume across restarts via the .omx/state/pipeline-state.json store.
  • Provides an API to build autopilot pipelines and run them programmatically.
  • Integrates with other OMX modes such as autopilot, team, and ralph for end-to-end workflows.

Quick Start

Create an autopilot pipeline configuration and run it to start the default OMX stages.

Frequently Asked Questions about pipeline

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

FAQPage Schema
How do I resume a multi-stage workflow after a system restart?

To resume a multi-stage workflow after a restart, the pipeline orchestrator persists progress in .omx/state/pipeline-state.json. This allows large-scale automation to reliably restore state and retry failed stages without losing prior execution context.

What is a PipelineStage interface and how does it coordinate automation tasks?

A PipelineStage interface is a defined contract that automation stages implement to share context and results. It ensures consistent sequencing across multi-stage workflows by reconciling configuration through a unified execution structure.

How do I orchestrate an OMX pipeline programmatically using built-in stages?

You can orchestrate an OMX pipeline programmatically by creating an autopilot pipeline configuration. The system applies the default ralplan, team-exec, and ralph-verify stages, running them sequentially to ensure consistent execution.

Does the pipeline orchestrator require specific dependencies to manage state persistence?

No specific external dependencies are required to manage state persistence. The pipeline orchestrator handles state internally by writing directly to the .omx/state/pipeline-state.json file, ensuring reliable resumability.

Can I use custom stages with the OMX workflow orchestration sequence?

Yes, you can use custom stages by implementing the reusable PipelineStage interface. This allows your custom logic to share context and results with the default ralplan, team-exec, and ralph-verify stages.

What is the best way to handle consensus planning and team execution in large-scale automation?

The best way to handle consensus planning and team execution is using a resilient pipeline that orchestrates the ralplan and team-exec stages. This ensures reliable retries, state restoration, and consistent sequencing across large-scale workflows.