dsh-cleaning-freq
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-cleaning-freq
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-cleaning-freq in your terminal to install this plugin; the source repository is at https://github.com/uckkk/dsh-cleaning-freq .
About this plugin
Deciding how often to clean something has long been a matter of gut feel—how often to wipe surfaces, how long between filter changes, what cadence suits which material. Answers vary from person to person and rarely carry a quantitative anchor. dsh-cleaning-freq turns that fuzzy judgment into a repeatable parameter calculation: feed in the relevant conditions and the tool returns a clear frequency recommendation, so you no longer have to guess.
The core capability is a single tool, cleaning_freq. It computes a precise frequency from the parameters you pass in and returns a definitive suggestion—nothing more, nothing less. Built in pure Node.js with zero network dependencies, it is ready to invoke in a session right after installation, with no external services and no configuration overhead.
Who is it for? If you are orchestrating routine or ops-style tasks in an agent workflow and want to turn periodic cleaning from a verbal agreement into a computable, traceable step, this plugin fills that gap. It does not schedule and does not push reminders; it simply converts parameters into a frequency number and leaves the rest to your workflow.
Use Cases
- Quantify periodic cleaning tasks into computable frequency steps within an agent workflow
- Quickly obtain a cleaning-cycle recommendation from material and environment parameters
- Make frequency decisions offline without any external service calls
Best For
- Developers orchestrating routine or ops tasks via agent workflows
- Teams that want to turn verbal cleaning agreements into traceable steps
- Node.js users who prefer zero-network, lightweight tools
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.