dsh-stain-mix
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-stain-mix
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness by running dsh plugin install uckkk/dsh-stain-mix; the repository is available at https://github.com/uckkk/dsh-stain-mix.
About this plugin
You want to mix your own no-nonsense cleaner but keep second-guessing the ratios. dsh-stain-mix removes that guesswork: hand it the relevant parameters and it hands back a precise recipe.
The plugin does one thing well: it calculates exact quantities and proportions for a cleaning formula based on the parameters you provide, then returns a clear, actionable recommendation. The whole implementation is pure Node with zero network calls, so it runs quietly and deterministically on your own machine.
It is a good fit for anyone who prefers DIY cleaning over commercial products, wants to avoid unnecessary additives, or simply needs a quick ratio check mid-conversation without pulling up a spreadsheet. Use it, get the answer, move on.
Use Cases
- Mixing a no-additive kitchen cleaner and needing exact ingredient quantities
- Quick ratio check mid-conversation without opening a spreadsheet
- Verifying whether a shared parameter set yields the correct cleaning proportions
Best For
- DIY cleaners who want to avoid unnecessary additives
- Users who need a quick ratio lookup mid-conversation
- People who prefer local-first tools with zero network calls
Related Plugins
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.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.