xby-todolist
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
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.