dsh-retro
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-retro
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-retro in the DeepSeek Harness terminal to install this plugin; source repository at https://github.com/uckkk/dsh-retro
About this plugin
After an agent workflow finishes a task cycle, the hardest part is often not execution but reflection. dsh-retro turns that reflection into a single tool call: describe the scenario and get back structured retrospective methods and actionable suggestions, eliminating the need to improvise a framework every time.
The plugin is a pure Node.js implementation with zero network calls, so it runs fast and works fully offline. Once installed, you simply invoke the retro tool inside your conversation and the results appear immediately with no extra configuration or dependency management.
It is ideal for developers who already orchestrate agent workflows with dsh, or for teams that want to make post-run reflection a fixed cadence rather than a one-off brainstorm. MIT licensed, zero dependencies, ready to use out of the box.
Use Cases
- Invoke structured retro methods after an agent completes a task cycle
- Generate a quick retrospective framework before team iteration meetings
- Retrieve retrospective guidance in fully offline environments without network access
Best For
- Developers already orchestrating agent workflows with dsh
- Teams that want post-run reflection as a fixed cadence rather than an ad-hoc brainstorm
- Users who prefer zero-dependency, offline-capable lightweight 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.