dsh-text-wrap
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-text-wrap
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-text-wrap in DeepSeek Harness to install the plugin; full source is available at https://github.com/uckkk/dsh-text-wrap
About this plugin
Long text output in model inference often needs deliberate line-wrapping, and dsh-text-wrap is a lightweight plugin built for exactly that. It is implemented in pure Node.js with zero network calls and zero external services, so every wrapping operation stays entirely on your machine.
The plugin registers itself as a session tool, and a single invocation is all it takes to wrap text according to the defined rules. There is no overhead, no dependency tree to maintain, and no data ever leaves the local environment.
It is a good fit for developers who need precise line-wrapping control in inference output while insisting on offline operation and a minimal dependency footprint.
Use Cases
- Controlling line-wrapping of long inference outputs
- Formatting text offline without any network dependency
- Quick in-session text reflow with zero setup overhead
Best For
- Inference developers who need precise line-break control
- Offline-first users who require zero network calls
- Plugin consumers who prefer minimal dependencies and no hidden costs
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.