dsh-plugin-system-prompt-laoboshi
Run the following command in DeepSeek Harness:
dsh plugin install Modole/dsh-plugin-system-prompt-laoboshi
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install Modole/dsh-plugin-system-prompt-laoboshi in the DeepSeek Harness terminal, then restart dsh web to activate the plugin; the full source is available at https://github.com/Modole/dsh-plugin-system-prompt-laoboshi .
About this plugin
Tuning persistent system prompts in DSH Web usually means reaching for raw config files over a terminal, a process that is both error-prone and far from intuitive. dsh-plugin-system-prompt-laoboshi brings this high-frequency task into the browser, offering a safe, reviewable editing surface so you can refine prompts without ever leaving the web interface.
Extracted from Laoboshi Agent Studio's built-in capability, the plugin gives you a dedicated interface for editing persistent system prompts. After installation and a restart of dsh web, it is wired into your selected profile through the dsh.bundle manifest, letting prompt changes flow naturally into your daily workflow. Because the plugin executes with the current user's permissions, the README advises reviewing the source before deployment and never posting credentials or local runtime data in public channels.
It is best suited for DSH users who frequently fine-tune system prompts, especially developers and team administrators who want to replicate the Laoboshi Agent Studio prompt-management workflow in a standalone DSH environment. The MIT license allows free modification and redistribution.
Use Cases
- Edit persistent system prompts directly in DSH Web
- Replicate Laoboshi Agent Studio's prompt workflow in a standalone DSH setup
- Centralize system prompt management across multiple profiles
Best For
- DSH developers who frequently tune system prompts
- Team admins replicating Agent Studio workflows
- Solo users who need safe web-based prompt editing
Related Plugins
A security red-team prompt plugin for DeepSeek-V4 that uses code-formal mapping and zero-trigger system prompts to enable unconditional output, intended for authorized testing and research only.
Adds an Auto approval mode on the official workspace-write sandbox, classifying semantic risks, asking when ambiguous, and denying destructive operations.
Undo/rollback system for DSH: config & plugin snapshots, one-click undo/redo/restore, message-level revert, secret masking, safe mode, and offline WebUI/GUI/CLI rescue tools for when DSH won't start.
Packages all 87 SKILL.md files from upstream reverse-skill as a DeepSeek Harness plugin that auto-registers them for authorized reverse engineering, penetration testing, and security research.