planning-with-files

Creates and manages task_plan.md, findings.md, and progress.md files for persistent task planning.

Updated Feb 15, 2026
One-click install
npx skills add https://github.com/Shawn-Guo-CN/agentfoundry-plugin-marketplace --skill planning-with-files-shawn-guo-cn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/Shawn-Guo-CN/agentfoundry-plugin-marketplace/tree/main/plugins/planning-with-files/.cursor/skills/planning-with-files
Command: npx skills add https://github.com/Shawn-Guo-CN/agentfoundry-plugin-marketplace --skill planning-with-files-shawn-guo-cn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of maintaining context and progress over long, complex tasks by using persistent markdown files as external memory, preventing information loss and ensuring task continuity.

Core Features & Use Cases

  • File-Based Planning: Utilizes task_plan.md, findings.md, and progress.md for structured task management.
  • Session Recovery: Automatically attempts to recover context from previous sessions.
  • Use Case: When embarking on a multi-day research project or a complex software development task involving numerous tool calls, this Skill ensures that all progress, findings, and decisions are persistently stored, allowing for seamless resumption and reducing the risk of forgetting critical details.

Quick Start

Before starting any complex task, create task_plan.md, findings.md, and progress.md using the provided templates.

Frequently Asked Questions about planning-with-files

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

FAQPage Schema
How do I maintain context and progress over long, complex agent workflows?

To maintain context over long agent workflows, use a file-based planning system that stores task phases, research findings, and session logs in persistent markdown files like `task_plan.md` and `progress.md`.

What's the best way to recover context from previous multi-day research sessions?

Recovering context from previous multi-day research sessions is handled automatically by reading persistent `findings.md` and `progress.md` files, allowing seamless resumption without losing critical discoveries.

How to manage multi-step software development tasks using markdown files?

Manage multi-step software development tasks by creating and updating `task_plan.md` for task phases, `findings.md` for discoveries, and `progress.md` for session logs to ensure robust state tracking.

Do I need any specific dependencies to implement file-based task persistence?

No specific dependencies are required to implement file-based task persistence; it operates by creating and managing standard markdown files directly within your project directory.

When should I use markdown-based planning instead of standard in-memory agent state?

You should use markdown-based planning instead of in-memory state when embarking on complex, multi-step tasks involving numerous tool calls where preventing information loss and ensuring session recovery is critical.