skills.rest
vadimcomanescu
vadimcomanescuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

planning-with-files

Track multi-step project progress in persistent markdown files.

24|8|Updated Jan 14, 2026
Search Tags:#planning#markdown#task-management#knowledge-management#files#project-tracking#agent-workflow
One-click install
npx skills add https://github.com/vadimcomanescu/codex-skills --skill planning-with-files-vadimcomanescu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-with-files
Source: https://github.com/vadimcomanescu/codex-skills/tree/main/skills/.experimental/product/planning-with-files
Command: npx skills add https://github.com/vadimcomanescu/codex-skills --skill planning-with-files-vadimcomanescu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Complex, multi-step tasks and research workflows lose context in chat-based interactions and exceed model context windows, making it hard to track progress, errors, and decisions across many iterative steps. This Skill provides a filesystem-backed pattern to keep goals, status, and findings durable and instantly retrievable so the agent never "forgets" the plan or hidden state.

Core Features & Use Cases

  • Persistent Plan File: Maintain a task_plan.md that records goals, phases, status, decisions, and error traces and is re-read before major decisions to refresh agent attention.
  • Three-File Pattern: Use a small set of files (task_plan.md, notes.md, deliverable) to separate planning, gathering, and final output for reproducible workflows.
  • Error Recovery & Observability: Append failure traces and recovery actions to the plan to surface issues and enable robust troubleshooting.
  • Use Cases: Research summaries, multi-phase feature development, complex bug fixes, and any task where iterative progress tracking and external memory are required.

Quick Start

Create a task_plan.md and notes.md, ask the assistant to follow the plan, read task_plan.md before each decision, and update it as you make progress.

Frequently Asked Questions about planning-with-files

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

FAQPage Schema
How do I track progress on complex multi-step projects without losing context?▼

Persistent markdown files provide durable external memory for project tracking, maintaining goals, status, and decisions across iterative steps so context is never lost. This prevents complex workflows from exceeding model context windows during execution.

What is the three-file pattern for agent workflow planning?▼

The three-file pattern uses task_plan.md for planning, notes.md for gathering findings, and a deliverable file for final output. This workflow structure separates iterative progress tracking from research storage to produce reproducible agent-driven results.

How to manage error recovery and trace failures during feature development?▼

Error recovery is managed by appending failure traces and recovery actions directly to a persistent task_plan.md file. This surfaces hidden state issues during feature development and enables robust troubleshooting by keeping error context instantly retrievable.

Can I use markdown files for knowledge management in agent-driven work?▼

Yes, markdown files support knowledge management in agent-driven work by acting as a filesystem-backed pattern for storing large findings to disk. They provide durable, instantly retrievable external memory that satisfies read-before-decide loop requirements.

When do I need external durable memory for task management?▼

External durable memory is needed for complex tasks like multi-phase feature development, research summaries, and bug fixes where iterative progress tracking is required. It prevents losing decisions and hidden state when workflows exceed chat-based context limits.

Does planning with persistent files work for research tasks with large findings?▼

Yes, planning with persistent files works for research tasks by storing large findings to disk in a notes.md file. This keeps gathered data instantly retrievable and prevents large research outputs from exceeding model context windows during analysis.

Related Skills

Explore More Product & Management Skills→
BaGyun0107BaGyun0107

deepinit

Automate project documentation and initial configurations from markdown workflows.

Community
Intermediate
pyinxpyinx
14

planning-with-files

Plan and track complex projects using persistent Markdown files.

Community
Advanced
Clay-HHKClay-HHK
2

planning-with-files

Track multi-step task progress using persistent markdown files.

Community
Advanced
faustellar1995faustellar1995
1

plan-mode

Generate, manage, and execute multi-step plans with progress tracking.

Community
Advanced