planning-with-files
A skill that keeps an AI coding agent's plan in files on disk so it survives context clears and long tasks. Helps agents stay on track and recover their progress across sessions.
Share on XLicense: MIT
Overview
planning-with-files is a skill that keeps an AI coding agent's plan in files on disk, so it survives context clears, compaction and crashes. It maintains task_plan.md, findings.md and progress.md, and lifecycle hooks inject selected planning context back into the session. It installs through npx skills or as a native plugin for hosts such as Claude Code, Codex CLI and OpenCode, and works with many agents through the Agent Skills standard.
Key features
- Keeps task_plan.md, findings.md and progress.md on disk
- Hooks re-inject planning context during the session
- Recovers the plan after /clear or compaction
- Installs via npx skills or native host plugins
Best for
Anyone running long agent tasks who loses track of the plan when the context window resets.
- Upstream
- OthmanAdi/planning-with-files
- Fork on GitHub
- Guo-astro/planning-with-files
- Upstream stars
- 27k
- Category
- AI agents and LLM tools
- Language
- Shell
- License
- MIT
- Forked
- 2026-01-05
- Sync status
- In syncLast synced 2026-09-29
More in AI agents and LLM tools
A free desktop app where children in non-English-speaking countries practice English speaking and listening by talking with an AI companion. It can run locally and offline.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
An agent skill for Chinese patents. It helps find patentable points, write disclosure documents, explain patents in plain language, follow policy changes and assist with examination replies.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
A minimal Python library from Hugging Face for building AI agents that write and run code to solve tasks. It lets you set up capable agents in a few lines.
Forked 2026-09-28Last synced 2026-09-29License: Apache-2.0AI agents and LLM toolsGitHub
An open-source benchmark that measures how well AI agents handle realistic legal work. It provides tasks and evaluation for improving legal agents.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub