Verified project record

OthmanAdi/planning-with-files

A file-based planning skill that gives AI coding agents persistent memory through task_plan.md, findings.md, and progress.md files. It enforces completion conditions via a Stop hook and secures plans with SHA-256 attestation.

Project overview

Project type: AI Agent
Use cases: Coding & Development · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developers and AI engineers working with AI coding agents on multi-step tasks who need persistent state and deterministic completion.

Key capabilities

Creates and maintains task_plan.md, findings.md, and progress.md for tracking phases, storing research, and logging sessions.
A Stop hook completion gate that holds the agent until all completion conditions are met.
Locks task_plan.md with a SHA-256 attestation to prevent tampering.

Limitations and risks

Not intended for simple questions, single-file edits, or quick lookups.
If file persistence is not maintained or utilized, AI agents may suffer from volatile memory and goal drift.

Getting started

Install the skill easily via a single command using npx. No coding is required for setup.

Evidence and sources

GitHub project description: Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completio…
README: planning-with-files is a persistent file-based planning skill for AI coding agents. It keeps task_plan.md, findings.md, and progress.md on disk so the agent survives context loss,…
README: | Claude Code | [Installation](docs/installation.md) | Plugin + SKILL.md + Hooks |
README: Claude Code (and most AI agents) suffer from: - Volatile memory — TodoWrite tool disappears on context reset - Goal drift — After 50+ tool calls, original goals get forgotten - Hi…
README: Formally evaluated using Anthropic's skill-creator framework (v2.22.0), model claude-sonnet-4-6, 2026-03-06. 10 parallel subagents, 5 task types, 30 objectively verifiable asserti…

Reviewed at: 2026-07-17T10:51:17Z