AI Agent Foreman: Supervise OpenCode with Flywheel Skill

AI Agent Foreman: Supervise OpenCode with Flywheel Skill

The AI Agent Foreman skill is designed to streamline the supervision of OpenCode worker processes, focusing on the mechanical execution side of work order dispatch, state monitoring, retry application, and escalations via the andon cord when deviations occur. This skill does not facilitate planning or inspection tasks but offers a structured approach to managing and supervising AI agent tasks across development teams.

What this skill does

• Dispatches each ready work order using the `flywheel log` for task preparation and `flywheel run` for execution.
• Monitors the state of each run operation, ensuring adherence to the specified briefs and applying the appropriate retry policy when necessary.
• Utilizes a fallback for single increment attempts to ensure a comprehensive review and execution of tasks while maintaining the logged event protocol compliance.
• Enables prompt escalation by activating the andon cord when anomalies or issues that cannot be classified arise.

Who it is for

• Software developers leveraging AI agents such as Claude Code, Cursor, and Codex in their coding and deployment workflows.
• Development teams looking for a reliable method to manage and supervise AI-driven coding processes with minimal manual intervention.
• Operation managers overseeing AI-driven software development environments.

Use cases

• Managing the execution of continuous integration pipelines where AI agents perform autonomous code writing and testing processes.
• Monitoring and controlling agent-driven software deployments by ensuring all procedural steps comply with predetermined operational protocols.
• Facilitating the oversight of complex coding projects distributed among different AI agents requiring detailed task handling and error management.

Technical details

• Leverages the Flywheel suite capabilities, specifically the `flywheel supervise` command for effective work order management.
• Ensures compatibility with OpenCode worker configurations, using specifications such as `skills/flywheel/references/worker-permissions.json` for task execution.
• Integrates within AI agent ecosystems supporting Claude Code, Cursor, and Codex environments to enhance the mechanical supervision of agents.

Source & Licence

This package is built on open-source work published by suzworx (suzworx/flywheel) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.