dsh-okr-split
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-okr-split
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-okr-split in your DeepSeek Harness terminal to install the plugin, whose full source code is available at https://github.com/uckkk/dsh-okr-split .
About this plugin
In agent workflows, OKR goal decomposition often relies on external services or network APIs, introducing extra latency and environment coupling. dsh-okr-split collapses this into a single local tool call: once the agent registers okr_split in a session, it passes parameters and immediately receives a structured, detailed decomposition result without waiting for any network round-trip.
The plugin is implemented in pure Node.js with zero network requests, keeping the call path short and the output fully deterministic. Whether you are building latency-sensitive automation pipelines or internal tool chains that must run offline, it delivers consistent computation results and eliminates the risk of external dependency failures interrupting your flow.
It is well suited for developers assembling agent workflows that need a decomposition step at a pipeline node, and for teams that want to move deterministic calculations out of external APIs to reduce maintenance overhead. Released under the MIT license, it can be freely integrated and extended.
Use Cases
- Decompose OKR goals by rules at an agent pipeline node
- Run deterministic objective decomposition offline with no network access
- Move OKR splitting from external API calls into a local tool invocation
Best For
- Developers building agent workflows that need a decomposition step
- Automation teams that value zero network dependency and low latency
- Engineers aiming to localize deterministic computations to cut maintenance overhead
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.