AI Agent Hub
Back to plugins
🧠

xby-todolist

Memory Updated 2026.09.02

Run the following command in DeepSeek Harness:

dsh plugin install xby-skill/xby-todolist

Paste the following prompt into your AI chat to install this plugin:

Install the plugin in DeepSeek Harness by running dsh plugin install xby-skill/xby-todolist; the source code is available at https://github.com/xby-skill/xby-todolist

About this plugin

When an AI agent tackles a multi-step development task, it runs into the natural ceiling of the context window: halfway through, earlier plans, pending items, and progress slowly slip out of memory, leading to missed steps, redundant work, or prematurely closing out unfinished tasks. xby-todolist exists to address exactly this gap, giving AI agents inside DeepSeek Harness a persistent external working memory layer.

At its core the plugin exposes a structured task read/write interface. todo_write creates entries with priority (high, medium, low) and status (pending, in_progress, completed), enforcing at most one in-progress task at any time; todo_read lets the agent pull the current list on demand to verify what remains. Together they let the agent continuously check its own progress during long, multi-step work, marking items done the moment they are finished, splitting blocked steps, and keeping context intact.

If you regularly ask an AI agent to handle multi-file refactors, batch code generation, or cross-module integration work that chains together several sub-steps, or if you simply want a live view of what is still incomplete mid-conversation, this plugin turns task management from a black box into a trackable workflow.

Use Cases

  • Tracking progress across multi-step refactoring tasks
  • Preventing early planning from being lost in long conversations
  • Managing pending items and priority ordering in batch code generation

Best For

  • Engineers who regularly assign multi-file multi-module tasks to AI agents
  • Developers who want real-time visibility into task completion status
  • Teams that need AI agents to reliably execute complex workflows