planning-with-files

Organizes complex tasks using persistent markdown planning files on disk.

1|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/Pgooone/oh-pgone-claudecode --skill planning-with-files-pgooone
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/Pgooone/oh-pgone-claudecode/tree/main/.claude/plugins/cache/planning-with-files/planning-with-files/2.23.0/.cursor/skills/planning-with-files
Command: npx skills add https://github.com/Pgooone/oh-pgone-claudecode --skill planning-with-files-pgooone

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Long multi-step tasks cause AI agents to lose track of goals after many tool calls, since context windows are volatile and limited. This Skill stores plans, findings, and progress in markdown files on disk so work survives context resets and session interruptions. ## Core Features & Use Cases - File-Based Planning: Creates task_plan.md, findings.md, and progress.md in your project directory to track phases, decisions, and errors. - Session Recovery: Detects unsynced context from previous sessions via a catchup script and supports automatic recovery after /clear. - Structured Error Handling: Enforces a 3-strike error protocol and error logging to prevent repeating failed actions. - Use Case: When asked to research a topic and produce a report, the agent creates a phased plan, logs discoveries after every search, and resumes cleanly even if the session is cleared mid-task. ## Quick Start Ask the agent to plan and break down your multi-step project using file-based planning before it starts working.

Frequently Asked Questions about planning-with-files

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

FAQPage Schema
How do I keep an AI agent on track during long multi-step tasks?▼

Use file-based planning: write the goal, phases, and decisions to a task_plan.md file on disk and re-read it before major decisions. This keeps goals in the model's attention window even after dozens of tool calls.

What files does file-based planning create in my project?▼

It creates three markdown files in your project root: task_plan.md for phases and decisions, findings.md for research discoveries, and progress.md for session logs and test results. Templates for each are included in the skill's templates directory.

Can planning files recover work after a session is cleared?▼

Yes. The skill includes a session-catchup.py script that detects unsynced context from a previous session. Combined with git diff and the existing planning files, the agent reconstructs state and continues from the current phase.

When should I not use file-based task planning?▼

Skip it for simple questions, single-file edits, and quick lookups. The overhead of creating and maintaining three planning files only pays off for tasks with three or more steps or many tool calls.

How does the 3-strike error protocol work?▼

On the first failure, diagnose and apply a targeted fix. On the second, try a different method or tool. On the third, rethink assumptions and update the plan. After three failures, escalate to the user with the specific error.