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.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
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
- 28k
- Category
- AI agents and LLM tools
- Language
- Shell
- License
- MIT
- Forked
- 2026-01-05
- Sync status
- In syncLast synced 2026-11-09
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-09License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-09License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-09License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-09License: Apache-2.0AI agents and LLM toolsGitHub