dsh-ui-models-invert-selection
Run the following command in DeepSeek Harness:
dsh plugin install FraYoshi/dsh-ui-models-invert-selection
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install FraYoshi/dsh-ui-models-invert-selection in DeepSeek Harness to install this plugin; the source code is available at https://github.com/FraYoshi/dsh-ui-models-invert-selection.
About this plugin
Auto-fetched provider lists can easily run into dozens or even hundreds of entries. Every time you need to add or adjust a batch of models, you end up clicking through a long wall of checkboxes item by item, scanning for the ones you already have. dsh-ui-models-invert-selection was built to eliminate that repetitive chore.\n\nWhat it does is straightforward: it adds a single Invert Selection button to the model-picking interface. One click flips every checkbox at once, instantly checking exactly the models you already own and unchecking the rest, so no more tedious one-by-one verification is needed.\n\nIt is ideal for DSH users who regularly manage models across multiple providers and frequently add or swap model configurations. The longer your list and the more models you juggle, the more this tiny button pays off in everyday workflow.
Use Cases
- Select all existing models from a long list in one click
- Bulk-uncheck unwanted model configurations
- Eliminate item-by-item clicking when frequently adding or removing models
Best For
- DSH users managing large model configurations
- Users maintaining models across multiple providers
- Ops personnel who prioritize everyday efficiency
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.