dsh-workspace-default-path
Run the following command in DeepSeek Harness:
dsh plugin install masknull/dsh-workspace-default-path
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install masknull/dsh-workspace-default-path in DeepSeek Harness to install this plugin, source code is at https://github.com/masknull/dsh-workspace-default-path
About this plugin
Every time you add a workspace in DSH, the browse dialog starts from the system home directory. When projects are scattered across deep folder trees, manually navigating back to the right spot on every add is a small but recurring interruption. dsh-workspace-default-path solves exactly one friction point: it remembers the path of your most recently added workspace so the next dialog opens right there, breadcrumb bar included.
Two lightweight hooks plug into the official flow: one watches the workspace list and records the path, the other redirects the dialog initial directory to the remembered one. Every other interaction, from browsing to confirming, stays fully official. A single toggle in Settings → General switches both hooks on or off; with it off, the plugin is completely inert. The setting hot-reloads into the running session with no restart.
Built for DSH users who switch between workspaces often or keep projects in deep directory structures. No extra runtime dependencies beyond what DSH already ships, no source modifications, MIT licensed.
Use Cases
- Skip repeated manual navigation when adding workspaces repeatedly
- Recover the last workspace path instantly in deep directory trees
- Standardize the workspace entry point across a team
Best For
- Power users who add or switch workspaces frequently
- Developers with deep or scattered project directories
- Efficiency-minded users who value small UX refinements
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.