dsh-whale
Run the following command in DeepSeek Harness:
dsh plugin install 1Lyn-en/dsh-whale
Paste the following prompt into your AI chat to install this plugin:
Install this plugin by running the command `dsh plugin install 1Lyn-en/dsh-whale` from its open-source address on GitHub at https://github.com/1Lyn-en/dsh-whale, then restart dsh web to activate it.
About this plugin
Conversational AI often drowns its core insights in pleasantries and padding, leading to longer wait times and inflated token costs. dsh-whale tackles this inefficiency head-on as a 'slim mode' plugin for DeepSeek Harness. Its core capability lies in intelligently trimming conversational filler—like articles, pleasantries, and hedging phrases—from AI responses. With multiple compression levels, from gently removing courtesies to aggressively fragmenting sentences into ultra-concise fragments (and even a classical Chinese mode), it allows users to dial in their preferred level of succinctness, achieving token savings of 60% to 75% without losing critical information.
More than a text compressor, dsh-whale transforms the user experience. It automatically activates a cyberpunk neon theme with sleek animations upon engagement, making efficiency visually engaging. The token savings are quantified in real-time after each response, while an automatic clarity safeguard ensures complex or high-stakes explanations are never oversimplified. It is an ideal companion for developers, technical writers, and power users who engage in frequent coding assistance, documentation search, or rapid Q&A sessions. For those who value speed, cost-effectiveness, and a touch of stylistic flair in their AI interactions, dsh-whale offers a compelling and practical enhancement to the DeepSeek Harness workflow.
Screenshots
Use Cases
- Engaging in daily coding Q&A or debugging for rapid core solutions
- Searching technical docs or APIs, wanting to bypass verbose explanations
- Monitoring AI service costs and aiming to significantly reduce output token usage
Best For
- Programmers and tech writers who frequently use DeepSeek Harness
- Power users focused on efficiency and cost in AI interactions
- Explorers interested in personalized UIs and visual styles like cyberpunk
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.