dsh-missher-enhance
Run the following command in DeepSeek Harness:
dsh plugin install Missher12/dsh-missher-enhance
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, ask your Agent to install Enhance from https://github.com/Missher12/dsh-missher-enhance following AGENT_INTEGRATION.md, then verify it in the Harness host you are currently using.
About this plugin
The official DeepSeek Harness covers the core model-conversation flow, yet in high-frequency daily use, cross-session information flow, cost transparency, document handling, and quick projectless chats often require users to patch things together. Enhance fills those gaps as a standalone plugin without interfering with the host or being tied to Desktop.
Its capabilities center on everyday efficiency: usage and cost statistics surface beneath the composer and in the settings panel; a piano-style conversation navigator makes long-session jumps intuitive; projectless sessions let lightweight discussions skip the project-creation step entirely; document workflows and cross-session messaging pull scattered context back onto one working surface; personal instructions and model metadata helpers reduce repetitive configuration. Every module toggles independently, and disabling one preserves all existing sessions, documents, and message records.
It is aimed at Harness users who run many conversation rounds per day, juggle multiple topics in parallel, and have clear needs around cost visibility and document flow. The plugin neither replaces the host nor introduces a second provider dependency tree — install and go, remove and clean.
Use Cases
- Quickly locate and jump between nodes in long multi-turn conversations
- Run lightweight projectless discussions and rapid Q&A without setup
- Relay messages, attachments, and document context across sessions
Best For
- High-frequency Harness users with daily multi-turn conversations
- Users juggling multiple discussion topics in parallel
- Users who track usage costs and document flow efficiency
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.