dsh-task-estimate
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-task-estimate
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-task-estimate, source code at https://github.com/uckkk/dsh-task-estimate
About this plugin
In any agent workflow, the first critical question during the planning phase is almost always "how long will this take?" When that answer still relies on gut feeling, every downstream schedule loses a reliable anchor. dsh-task-estimate narrows duration estimation down to a single deterministic tool call, turning planning from a vague guess into a reproducible calculation.
Built entirely in Node.js, the plugin registers a task_estimate tool that accepts structured task parameters and returns a detailed, well-formed estimate. The whole computation runs locally with zero network dependencies, making it fast, deterministic, and fully usable in offline environments.
If you are assembling an agent workflow and need quick, repeatable task-duration estimates during the planning stage without spinning up extra services or incurring network overhead, dsh-task-estimate offers a lightweight, plug-and-play option that slots right into your existing toolchain.
Use Cases
- Quick task duration estimation during the planning phase
- Offline environments with no network access
- Feeding structured estimates into downstream scheduling
Best For
- Engineers building agent workflows
- Teams needing deterministic estimates in offline settings
- Developers who prefer lightweight, plug-and-play 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.