DSH-peak-valley
Run the following command in DeepSeek Harness:
dsh plugin install CreateCN/DSH-peak-valley
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install CreateCN/DSH-peak-valley in the DeepSeek Harness terminal to install the plugin; the source repository is at https://github.com/CreateCN/DSH-peak-valley.
About this plugin
Peak and valley windows for electricity rates or inference billing tend to slip by quietly, and checking a schedule by hand is both tedious and easy to miss. DSH-peak-valley turns that into a glanceable, always-on reminder: a small capsule tucked into the bottom-left corner of your screen.
The capsule color-codes the current window at a glance: green for valley, orange for peak, grey when no range has been set. A live countdown (Xh Ym until peak or valley) ticks along and refreshes automatically every 30 seconds, so there is nothing to click or monitor. Time ranges use the HH:MM-HH:MM format; an end time earlier than the start time crosses midnight (e.g. 16:30-00:30). Any edits are persisted to the DSH settings.yaml file and survive restarts.
If you schedule household electricity around off-peak tariffs, watch inference billing windows, or simply want to stop second-guessing whether it is peak or valley right now, this lightweight floating widget is the quickest way to keep that information always visible.
Use Cases
- Managing household electricity around peak and valley tariffs at a glance
- Confirming the current billing window before launching batch inference tasks
- Tracking overnight peak-valley transitions without repeatedly checking a schedule
Best For
- Home users optimizing electricity costs around off-peak tariffs
- Developers batching model inference during valley billing windows
- Efficiency-focused users who prefer lightweight widgets over heavy apps
Related Plugins
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.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.