AI Agent Hub
Back to plugins
🧠

dsh-pin-recall

Memory Updated 2026.08.15

Run the following command in DeepSeek Harness:

dsh plugin install kerwin2046/dsh-pin-recall

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

Run dsh plugin install kerwin2046/dsh-pin-recall inside DeepSeek Harness to install; the source is at https://github.com/kerwin2046/dsh-pin-recall .

About this plugin

In long multi-turn sessions, a critical tool output or assistant conclusion can easily get buried under subsequent turns. dsh-pin-recall lets you pin any reply, tool result, or free-form text directly in the session and recall it back into the model context with a single command, eliminating manual copy and paste.

The interaction works on two layers. In the Web UI, every finished assistant message shows a star toggle at the bottom; a corner-icon button then packages all pins and wakes the agent in one click. On the command side, /pin, /pins, /recall, and /unpin cover per-message, per-type (tool or assistant), and free-text granularity, with a quiet-queue option that enqueues without triggering a wake.

Built for developers running deep reasoning chains, debugging tool calls, or repeatedly referencing early conclusions inside DeepSeek Harness, so the evidence trail stays one recall away.

Use Cases

  • Reusing early tool outputs across a long reasoning chain
  • Quickly recalling key conclusions while debugging multi-turn agents
  • Anchoring assistant replies as context for subsequent turns

Best For

  • Developers running long reasoning chains in DeepSeek Harness
  • Agent debuggers who repeatedly reference early conclusions
  • Engineers mixing Web UI and CLI workflows