dsh-fear-pet
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-fear-pet
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-fear-pet in DeepSeek Harness to install this plugin; the source is available at https://github.com/uckkk/dsh-fear-pet.
About this plugin
When fear or anxiety hits, what you really need is not a wall of text but a single, concrete, actionable prompt. dsh-fear-pet was made for exactly that moment: it plugs into your model-inference chain, takes the parameters you pass in, and returns a targeted behavior-correction suggestion, turning the question of what to do next into a step you can actually follow.
Its core capability is deliberately narrow: accept parameters, output advice, nothing more. Implemented in pure Node.js with zero network dependencies, it runs fully offline, keeps your data on-device, and never breaks because of a dropped connection. For anyone who wants to embed an emotion-intervention stage into a local inference pipeline, it is a drop-in module with no extra configuration.
Who is it for? If you are building a local LLM application and want a built-in calm-and-guide step in the flow, or if you personally deal with mild anxiety and want a tool you can call on demand without sending data to the cloud, dsh-fear-pet slots right in. MIT licensed, so you are free to use it anywhere.
Use Cases
- Embedding an emotion-intervention step into a local inference chain
- Quickly getting an actionable behavior correction tip during anxiety
- Calling an emotion-soothing tool without network access
Best For
- Developers building local LLM apps who need a built-in calming step
- Privacy-sensitive users who want data to never leave the device
- Integrators looking for a lightweight zero-config emotion module
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.