dsh-global-task-list
Run the following command in DeepSeek Harness:
dsh plugin install sgzxs/dsh-global-task-list
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command `dsh plugin install sgzxs/dsh-global-task-list`; the full source code is available at https://github.com/sgzxs/dsh-global-task-list.
About this plugin
In intricate AI agent workflows, task management often vanishes when a session ends, leading to fragmented progress and collaboration. The dsh-global-task-list plugin addresses this by providing a persistent global task library for DeepSeek Harness. It allows you to create, update, and track tasks that survive across sessions and restarts, thanks to backend storage. Core capabilities include five model-facing CRUD tools (e.g., task_add and task_list) for direct task manipulation, a persistent browser panel that displays real-time task statuses with manual control, and automatic synchronization of subagent job statuses to keep background tasks aligned. Tasks can also carry structured documents, rendered as generative UI elements like progress bars or timelines. This plugin is ideal for developers or AI application builders using DeepSeek Harness who need robust task orchestration, persistent memory, and visual management—transforming ad-hoc task tracking into a systematic, reusable asset.
Use Cases
- Persistently track complex task progress across multiple sessions
- Manage subagent job statuses in AI agent workflows
- Visualize task data and status changes through generative UI
Best For
- AI developers and architects using DeepSeek Harness
- Engineers building multi-agent systems needing persistent memory
- AI application designers seeking task visualization and interactive interfaces
Related Plugins
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.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.