othmanadi avatar

Pi Planning With Files

If you're working on anything that takes more than a handful of steps, this gives Claude persistent memory through three markdown files: task_plan.md for your roadmap, findings.md for discoveries, and progress.md for tracking what's done. The standout feature is session recovery. Run a Python script after you `/clear` the conversation and Claude picks up right where it left off by reading those files back in. It enforces a workflow: plan first, update after each phase, log errors, and never retry the same failed action twice. There's a three-strike protocol for debugging and templates to keep things structured. Basically turns your project directory into Claude's external brain so context survives across sessions.

skills.sh installs
10.5K
GitHub stars
28K
last updated
Aug 21, 2026

Install

$ npx -y skills add othmanadi/planning-with-files --skill pi-planning-with-files --agent claude-code

Installs into .claude/skills of the current project.

Files

If you're working on anything that takes more than a handful of steps, this gives Claude persistent memory through three markdown files: task_plan.md for your roadmap, findings.md for discoveries, and progress.md for tracking what's done. The standout feature is session recovery. Run a Python script after you `/clear` the conversation and Claude picks up right where it left off by reading those files back in. It enforces a workflow: plan first, update after each phase, log errors, and never retry the same failed action twice. There's a three-strike protocol for debugging and templates to keep things structured. Basically turns your project directory into Claude's external brain so context survives across sessions.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/othmanadi/planning-with-files
Categories
Code Review & Quality, Data Science & ML, Productivity & Planning

More from othmanadi/planning-with-files

All 7
1imbad0202 avataracademic-paper-reviewerimbad0202/academic-research-skillsMulti-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (Journal-Fit Reviewer + 3 peer reviewers + Devil's Adv10.3Kskills.sh installs
2github avataragentic-evalgithub/awesome-copilotPatterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluat10.3Kskills.sh installs
3cursor avatardeslopcursor/pluginsRemove AI-generated code slop and clean up code style10.2Kskills.sh installs
4ljagiello avatarctf-pwnljagiello/ctf-skillsProvides binary exploitation techniques for CTF challenges. Use when you already have a vulnerable native target or service and need to turn memory corruption o10.1Kskills.sh installs
5wshobson avatarteam-communication-protocolswshobson/agentsStructured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Us10Kskills.sh installs
6github avatarpowerbi-modelinggithub/awesome-copilotPower BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schem10Kskills.sh installs