dsh-output-styles
Run the following command in DeepSeek Harness:
dsh plugin install auggie246/dsh-output-styles
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install auggie246/dsh-output-styles in your terminal to install the plugin; the repository is at https://github.com/auggie246/dsh-output-styles. After installing, restart dsh web and open Settings to access the Output Style page.
About this plugin
Spending time on the prompt rather than the task is a daily drag when orchestrating multiple AI agents in DeepSeek Harness. The web settings treat the system prompt as a fixed block, so shifting the tone of every agent's replies means editing config and restarting the session. dsh-output-styles exists to remove that friction by turning output style into a first-class, switchable setting.
Use Cases
- Standardize output tone across multiple agents without repeating instructions every turn
- Switch between concise, explanatory, learning, or formal presets on the fly
- Paste a team style file and save it as a named, persistent output style
Best For
- Developers running multi-agent workflows in DeepSeek Harness Web
- Tech leads standardizing AI output conventions across a team
- Users migrating output style configurations from Claude Code to Harness
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.