dsh-workspace-prompts
Run the following command in DeepSeek Harness:
dsh plugin install Fayelin12/dsh-workspace-prompts
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install Fayelin12/dsh-workspace-prompts in your terminal to install the plugin; the source is available at https://github.com/Fayelin12/dsh-workspace-prompts. Restart dsh web after installation.
About this plugin
When you run several workspaces side by side in DeepSeek Harness, each project may carry its own tech stack, coding conventions, and collaboration rules, yet the system prompt remains global. dsh-workspace-prompts lets you attach one custom system prompt per workspace; when a new session is created, the prompt is captured into that session, layered on top of the fixed system prompt. Each workspace stays independent, so conventions never bleed across projects.
Key capabilities include: an inline dialog in the session header for full CRUD and activation of workspace prompts; data persisted in a .workspace-prompts.json file at the workspace root, safe across restarts and project migrations; capture-at-creation semantics that freeze the prompt version for existing sessions to prevent behavioral drift over time; and Agent-facing tools (workspace_prompt_get / workspace_prompt_set) so the model can autonomously read or update the current workspace prompt without any UI interaction.
Ideal for developers who manage multiple DSH workspaces concurrently and want per-project system-prompt overrides to persist, such as team coding standards, output-format preferences, or domain-specific constraints that the Agent should always follow.
Use Cases
- Managing multiple DSH workspaces with distinct coding conventions and output formats
- Version-controlling team-level system prompts alongside the project repository
- Letting the Agent autonomously read and update the current workspace prompt without manual UI interaction
Best For
- Developers running multiple DSH workspaces in parallel
- Users who want workspace-level prompts persisted to disk and surviving restarts
- Users who prefer Agent-driven prompt management over manual dialog interaction
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.