OthmanAdi/planning-with-files

This page introduces an external open-source repository. It is not an HDATF product.

What it does

An agent skill that keeps task_plan.md, findings.md and progress.md on disk and uses lifecycle hooks to re-inject the plan every turn, so coding agents can resume after /clear, crashes or context compaction.

How it helps ATF

Close to what Harness does in keeping goal, state and memory for one AI task. Its plan files, per-turn re-injection and completion gate could be a reference for holding task state outside the context window and deciding when work is done.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• ChrisWiles/claude-code-showcase
  An example Claude Code project setup with skills that describe team conventions, hooks that format code, run tests and block edits on the main branch, a code review agent, and GitHub Actions workflows for PR review.
• kepano/obsidian-skills
  Agent skills that teach agents such as Claude Code, Codex and OpenCode to work with Obsidian through its CLI and open formats, including Markdown, Bases and JSON Canvas. They follow the Agent Skills specification.
• vercel-labs/agent-skills
  A collection of skills for AI coding agents in the Agent Skills format, each packaging instructions, scripts and notes on when to use it. Examples cover Vercel cost and performance audits, React and Next.js performance rules, and web interface review.
• ComposioHQ/awesome-claude-skills
  A curated list of Claude skills and plugins grouped into areas such as document processing, development tools, data analysis, business and communication, plus a plugin that connects Claude to outside apps through Composio.
• different-ai/openwork
  An open-source desktop app for sharing AI workflows. Its MCP lets agents such as Codex or Claude Code search and run shared skills, MCP connections and services, and an admin interface manages access and connections.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.