dsh-shallow-clone
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-shallow-clone
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-shallow-clone in DeepSeek Harness to install; full source is available at https://github.com/uckkk/dsh-shallow-clone
About this plugin
Shallow cloning is a high-frequency yet tedious operation in agent inference sessions: you need a copy of an object without the cost of a deep clone or extra dependencies. dsh-shallow-clone wraps this step into a ready-to-use session tool, so you get a shallow-copied result with a single call instead of hand-writing JavaScript snippets every time.
The plugin is implemented purely in Node with no network calls and no third-party runtimes. After installation it registers as a session tool, ready to be invoked from prompts or tool chains to produce a one-level copy instantly.
It is well suited for developers who frequently handle object snapshots, perform shallow merges, or derive new state during inference, especially in setups where keeping the toolchain lightweight and free of network requests matters.
Use Cases
- Generating quick object copies during agent inference
- Shallow merging or deriving state without deep cloning
- Keeping the toolchain lightweight with zero network calls
Best For
- Developers who frequently handle object snapshots
- Teams seeking a lightweight, zero-network toolchain
- Agent developers integrating JS utility functions in prompts
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
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.