deepseek-harness-zcode_mask
Run the following command in DeepSeek Harness:
dsh plugin install magian1127/deepseek-harness-zcode_mask
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness by running dsh plugin install magian1127/deepseek-harness-zcode_mask; the source code is available at https://github.com/magian1127/deepseek-harness-zcode_mask .
About this plugin
In DeepSeek Harness model-inference pipelines, certain workflows require masking of zcode-related fields to prevent sensitive data from surfacing during inference. deepseek-harness-zcode_mask is a lightweight plugin built for exactly that purpose, integrating zcode masking logic into the inference pipeline in a standardized way.
Its core responsibility is tightly focused: performing mask operations on zcode-related data during the model-inference stage, allowing the Harness pipeline to retain full functionality while meeting data-concealment requirements. The plugin follows the DeepSeek Harness plugin specification, so it drops in without extra adaptation work.
If you are running model inference on DeepSeek Harness and your workflow involves zcode field anonymization or masking, this plugin lets you fold that step into a unified framework and cut down on the maintenance burden of one-off scripts.
Use Cases
- Masking zcode fields within the DeepSeek Harness inference pipeline
- Preventing sensitive zcode data from surfacing during model inference
- Completing zcode anonymization in a unified framework to reduce custom script overhead
Best For
- Developers running model inference on DeepSeek Harness
- AI engineers who need zcode anonymization in their inference pipeline
- Teams looking to centralize data-masking logic and reduce maintenance overhead
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.