Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
Description collected from the plugin's own repository or package metadata.
npx @deepseek-ai/dsh plugin add @zoria-lind/dsh-token-optimizer
@PerryLink
Cross-platform native desktop control tools for DeepSeek Harness (Windows first): screenshot, screenread (accessibility tree + pixel description for text-only models), click/type/scroll/key, and applist/applaunch - every mutating action gated by appro
@PerryLink
Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.
@miuzel
DeepSeek Harness (dsh) plugin that organizes work into goal kanban boards: a two-dimensional swimlane board of goals / criteria / context cards / execution attempts, with data stored as files and event streams in .dsh-graph - Goal-kanban plugin for DeepSeek Harness