skills.rest
Herxinsasa
HerxinsasaCOMMUNITY
Explore all skills by this author →
GitHub

pi-planning-with-files

Track multi-step task progress across context resets using persistent markdown files.

1|Updated Apr 22, 2026
Search Tags:#planning#markdown#context-management#task-tracking#session-recovery#agent-workflow#error-logging
One-click install
npx skills add https://github.com/Herxinsasa/Skills-Collector --skill pi-planning-with-files-herxinsasa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pi-planning-with-files
Source: https://github.com/Herxinsasa/Skills-Collector/tree/main/planning-with-files/.pi/skills/planning-with-files
Command: npx skills add https://github.com/Herxinsasa/Skills-Collector --skill pi-planning-with-files-herxinsasa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Long, complex AI agent tasks often suffer from volatile context windows that lose progress, cause goal drift, and hide errors, leading to incomplete or incorrect results. This Skill solves that problem by using persistent markdown files as external working memory, ensuring all progress, decisions, and findings are saved to disk and accessible even after context resets.

Core Features & Use Cases

  • 3-File Planning System: Automatically creates and maintains task_plan.md for phase tracking, findings.md for research and decisions, and progress.md for session logs.
  • Session Recovery: Includes a script to recover unsynced context from previous sessions after a context clear, so you can resume work seamlessly.
  • Error & Progress Tracking: Enforces logging all errors, tracking failed attempts, and re-reading plans before major decisions to prevent repetition and goal drift.
  • Use Cases: Ideal for multi-step software development tasks, research projects, bug fixes, feature implementation, and any work requiring 5 or more tool calls.

Quick Start

Invoke the planning-with-files skill to organize and track progress on your complex multi-step project.

Frequently Asked Questions about pi-planning-with-files

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

FAQPage Schema
How do I prevent context loss and goal drift in AI agent workflows during long complex tasks?▼

Use a 3-file planning system to maintain task state across long complex tasks: task_plan.md for phase tracking, findings.md for research decisions, and progress.md for session logs. These files act as external working memory to eliminate context loss.

How do I recover unsynced context and resume work after an AI agent session reset?▼

Session recovery works by running a script that reads persistent markdown files to reload phase tracking, findings, and progress logs. This mechanism allows you to seamlessly resume multi-step work after a context clear.

When do I need file-based planning for multi-step software development tasks?▼

You need file-based planning for multi-step software development tasks, research projects, bug fixes, and feature implementations requiring 5 or more tool calls. It enforces error logging and re-reading plans to prevent repetition and goal drift.

Does this markdown planning approach work for tracking errors and failed attempts in agent workflows?▼

Yes, this markdown planning approach enforces logging all errors, tracking failed attempts, and re-reading plans before major decisions. This prevents repetition and goal drift during complex multi-step agent workflows.

What is the best way to maintain task state across context resets in AI agents?▼

The best way to maintain task state across context resets is implementing a 3-file markdown planning system with session recovery, error logging, and phase tracking. This persistent external memory eliminates volatile context window limitations.

Related Skills

Explore More Software Engineering Skills→
qiushibangqiushibang

planning-with-files

Persist task plans, findings, and progress in markdown files across sessions.

Community
Advanced
tiweentiween

bmad-quick-dev

Automate code development workflows from planning through review using predefined templates.

Official
Advanced
tdiminotdimino
41

planning-with-files

Manage complex tasks with persistent markdown planning files.

Community
Advanced
aram-devdocsaram-devdocs
6

session-continuity

Save session state to SESSION.md and restore context across interruptions.

Community
Intermediate