dsh-text-diff
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-text-diff
Paste the following prompt into your AI chat to install this plugin:
Run the plugin install command in your terminal to add dsh-text-diff to the local profile bundles list; full source: https://github.com/uckkk/dsh-text-diff
About this plugin
During model-inference sessions you often need to compare two pieces of text side by side—a code change, a document revision, a config difference—and the usual workaround is copying the content into a browser-based diff tool or spinning up a local service. dsh-text-diff pulls that step back inside the session: one call returns a line-level diff, with no intermediate hop.
The implementation is pure Node.js with zero network requests and no external diff service or bundler. Once installed, the plugin registers a tool in the dsh session that you can invoke at inference time whenever a text comparison is needed. It is lightweight, pulls in no transitive dependencies, and plays well in supply-chain-sensitive environments.
It is a natural fit for anyone whose dsh-based inference workflow involves frequent text comparison: code review, prompt iteration, or tracking revisions of structured documents. As long as your comparison targets are plain text lines, you get a clean add-delete-modify view without ever leaving the terminal.
Use Cases
- Line-level code change comparison
- Prompt version iteration diff
- Configuration file difference review
Best For
- dsh inference workflow users
- Code review and doc tracking practitioners
- Projects with local-execution security requirements
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.