dsh-code-review
Run the following command in DeepSeek Harness:
dsh plugin install satan9394/dsh-code-review
Paste the following prompt into your AI chat to install this plugin:
Install it in DeepSeek Harness by running dsh plugin install satan9394/dsh-code-review; source at https://github.com/satan9394/dsh-code-review.
About this plugin
Code review is one of the most time-consuming parts of daily development, and even experienced teams struggle to catch every edge case or maintainability issue under release pressure. dsh-code-review slots into the DeepSeek Harness plugin ecosystem to bring AI-powered code review directly into your workflow, letting the model handle the repetitive first pass so developers can focus on architecture and business logic.
Categorised under model-inference, the plugin leverages the semantic understanding and reasoning strengths of large language models to perform structured reviews of code changes. It surfaces potential logic errors, missing boundary conditions, and opportunities to improve readability and maintainability.
If you already use DeepSeek Harness in a team or personal setup and want an AI-assisted layer for code review, dsh-code-review offers a focused, lightweight option. Released under the MIT licence, it integrates seamlessly into CI pipelines or local development loops.
Use Cases
- Automate first-pass code review for pull requests in CI pipelines
- Quickly check code changes for logic and edge-case issues during local development
- Let AI handle the repetitive first pass in team code review workflows
Best For
- Developers already using DeepSeek Harness who want AI-assisted code review
- Engineering teams looking to reduce the manual code review burden
- Developers focused on code quality and maintainability
Related Plugins
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.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.