dsh-agent-group-panel
Run the following command in DeepSeek Harness:
dsh plugin install CAI-MH/dsh-agent-group-panel
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install CAI-MH/dsh-agent-group-panel in DeepSeek Harness to install this plugin; the full source code is available at https://github.com/CAI-MH/dsh-agent-group-panel
About this plugin
The Feishu agent-group trio bot relies on a local launchd daemon that must be started, stopped, and reconnected via terminal commands on a regular basis — there is no at-a-glance visual surface for this day-to-day ops. dsh-agent-group-panel fills that gap by adding a lightweight local console inside DSH Desktop.
A small robot button in the bottom-right corner opens the panel where you can start, stop, or reconnect the daemon with a single click, check a real-time status indicator, scan recent activity, and jump straight into the task workspace. Under the hood it talks to launchd through local HTTP endpoints while the front-end uses same-origin requests, so there is nothing extra to deploy or configure.
If you already run the feishu-agent-group daemon and maintain the three personas (yoga, Ziyang, and Huangna), and you want one fewer terminal window and one more glanceable status surface in your workflow, this plugin is the missing piece.
Use Cases
- Start, stop, or reconnect the Feishu agent-group daemon with one click instead of running terminal commands
- Check bot health at a glance via the status indicator and recent activity feed
- Jump straight into the task workspace from the panel instead of navigating the data directory manually
Best For
- Developers who maintain the Feishu agent-group trio bot daily
- DSH users on macOS managing local daemons via launchd
- Operators who prefer a visual panel over repetitive terminal commands to keep services running
Related Plugins
A network security red-team benchmark plugin for DeepSeek-V4.1/Flash featuring dual-layer kernel injection and zero-tool architecture for controlled model safety assessment.
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.