dsh-order-plan
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-order-plan
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-order-plan in the DeepSeek Harness terminal to install this plugin; source code is available at https://github.com/uckkk/dsh-order-plan
About this plugin
A hotpot dinner falls apart the moment the broth starts rolling and the table descends into chaos: who plunges the shrimp paste first, do the leafy greens go in as a base or later, and who is even in charge of the dipping-sauce station? dsh-order-plan exists to take that coordination burden off your plate. Feed it a set of parameters and it steps back with a sensible serving plan, sequencing which items hit the pot first, which share a round, and which save the show.
Under the hood the tool stays deliberately lean: it runs entirely in Node.js with no network calls whatsoever. There is no API to authenticate against, no external service to reach, and no timeout to chase. In an agent-workflow pipeline it simply registers as a local tool and answers immediately, making it a natural fit for air-gapped environments, internal deployments, or any architecture that treats one less HTTP round-trip as a feature.
Who will actually reach for it? Hosts who gather friends for hotpot on a regular cadence and are tired of improvising the order every time. Developers wiring a chat agent and want a plan-my-hotpot-sequence capability that just works offline. And systems architects who insist that every utility in their toolkit be lightweight, dependency-free, and MIT-licensed. Grab it, call it, walk away.
Use Cases
- Quickly sequence a hotpot dinner before a group gathering
- Invoke an ordering-plan tool inside an agent conversation
- Generate a timed serving schedule in a fully offline environment
Best For
- Hosts who organize regular hotpot dinners
- Workflow developers wiring local tools into chat agents
- Architects requiring offline, dependency-free utilities
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.