AI Agent Hub
Back to plugins
⚙️

dsh-queue-director

Workflow Updated 2026.08.17

Run the following command in DeepSeek Harness:

dsh plugin install loklamlok/dsh-queue-director

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

Run dsh plugin install loklamlok/dsh-queue-director in your DeepSeek Harness terminal to install this plugin; the source is hosted at https://github.com/loklamlok/dsh-queue-director.

About this plugin

When batch-submitting prompts or drafting a long-form article in DeepSeek Harness, queued messages are processed strictly in the order you submitted them, and reordering is awkward at best. dsh-queue-director was built to fix exactly that: every queued message gains up, down, move-to-top, and move-to-bottom controls, and you can also grab a row (or its dot handle) and drag it to any position in the queue, putting processing order entirely under your control.

Beyond reordering, the plugin adds a "Send all now" button that promotes every pending message to the AI in a single action (it works even while a task is running), and a two-step-confirm "Clear queue" button to prevent accidental data loss. All built-in behaviors — preview, inline edit, per-message remove, and send-now (steer) — are fully preserved. The plugin mounts as a bundle without modifying any DSH source; after an update a simple page refresh is all you need.

If you regularly batch-submit multi-prompt sequences, need to reorder sections while writing long-form content, or simply want to treat the queue as a lightweight workflow scheduler, this plugin saves real operational overhead and turns the queue from a passive FIFO list into an interactive, drag-and-drop sequence you command.

Use Cases

  • Processing a batch of prompts in your own priority order
  • Reordering sections while writing a long-form article with AI assistance
  • Promoting an urgent message to the front of a running queue

Best For

  • DeepSeek Harness users who regularly batch-submit multi-prompt sequences
  • Writers crafting long-form content with AI who need flexible section ordering
  • Developers who want to treat the queue as a lightweight workflow scheduler