dsh-asset-split
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-asset-split
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-asset-split in your DeepSeek Harness terminal to install this plugin; the source is available at https://github.com/uckkk/dsh-asset-split .
About this plugin
In agent-driven workflows, asset allocation, budget splitting, and resource distribution often require precise calculations based on fixed ratios or rules. Hand-coding this logic is error-prone and hard to reuse across sessions. dsh-asset-split packages this repetitive math into a single, reliable tool call, letting you focus on orchestration.
The core of the plugin is the asset_split tool: pass in a target total and the splitting parameters, and it returns a detailed breakdown for each segment. The entire implementation is pure Node.js with no external network dependencies, so it runs locally with fast response times, making it ideal for latency-sensitive or offline environments.
If you are building agent workflows that involve recurring asset allocation, cost apportionment, or resource pool division, dsh-asset-split can serve as a lightweight computation node, eliminating boilerplate code so you can concentrate on the orchestration logic itself.
Use Cases
- Splitting a budget total into fixed-ratio segments within an agent workflow
- Calculating precise cost apportionment shares for multiple parties
- Performing local resource pool division in an offline environment without network calls
Best For
- Developers building agent workflows that need embedded precise calculation steps
- Engineers handling repetitive math for asset splitting or budget allocation
- Offline workflow developers seeking local, zero-network-dependency 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.