dsh-tint
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-tint
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-tint in DeepSeek Harness to install the dsh-tint plugin; source code is available at https://github.com/uckkk/dsh-tint .
About this plugin
Color output in everyday model-inference sessions often feels flat and lacks visual depth. dsh-tint tackles exactly that small pain point by providing ready-to-use color-brightening tools, so you can improve how colors appear without ever leaving your current session.
The entire plugin is written in pure Node.js, carries zero third-party runtime dependencies, and makes no network requests whatsoever. All logic runs locally. Once installed, you simply invoke the tool the plugin registers from within your session to apply the brightening effect. No configuration, no setup, no external API calls.
It is well suited for developers who want a quick color-adjustment capability in their dsh plugin stack: no heavyweight graphics library, no external service, just a lightweight and offline-friendly brightening utility that adds minimal overhead to your workflow.
Use Cases
- Quickly adjust output color brightness in a model-inference session
- Run color-brightening tools locally without any network access
- Add color-adjustment capability to your dsh plugin stack with minimal overhead
Best For
- dsh plugin developers who need a lightweight color-adjustment tool
- Developers who prefer local execution and zero external dependencies
- Users who want to improve visual output in their model-inference workflow
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.