Persistent File-Based Planning for AI Coding Agents

Persistent File-Based Planning for AI Coding Agents: Your Reliable Memory Backup

Maintain a resilient workflow with the Manus-style Persistent File-Based Planning skill for AI coding agents like Claude Code, Cursor, and Codex. This specialized skill ensures that your work survives context loss and clears by persisting planning files on disk. Whether organizing a complex multi-step project or conducting extensive research, you can rely on the structured markdown files to seamlessly recover and continue your sessions.

What This Skill Does

This skill enables AI coding agents to work like a manuscript system, using persistent markdown files as a "working memory on disk." Here's how it works:

• Upon initiation, the skill checks for existing planning files: task_plan.md, findings.md, and progress.md.
• If unsynced context from a previous session is detected, the skill executes a session catchup script to reconcile any changes.
• Employs git commands like git diff --stat to review and update planning files based on file changes and session discrepancies.
• Automatic session recovery ensures continuity even after a /clear command.

Use Cases

Transform your AI coding projects into organized and manageable tasks with this skill:

• Software Development Teams: Break down large-scale coding projects into manageable tasks that persist over time.
• Research and Data Analysis: Keep track of findings and research steps for long-term data projects.
• Automated Project Management: Efficiently handle projects requiring multiple tool integrations and step-by-step planning.

Technical Details

This skill leverages the following tools and methods:

• Integration with AI coding agents: Claude Code, Cursor, and Codex.
• Persistent file management using markdown files: task_plan.md, findings.md, and progress.md.
• Automatic session recovery and catchup scripts for unsynced context on Linux, macOS, and Windows.
• Utilizes shell and Git commands to ensure accurate context restoration.

Supercharge your AI coding endeavors with the robust, context-preserving capabilities of Persistent File-Based Planning. Maintain your momentum and organize your tasks with ease!

Source & Licence

This package is built on open-source work published by OthmanAdi (OthmanAdi/planning-with-files) 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.