Skip to content
Plugin

dsh-kanban-flow

thomasvvugt51Updated 1mo ago

Open on GitHub

Agent-driven kanban board for DeepSeek Harness: one board per workspace, per-task agent sessions, guarded human/agent workflow

Practical score

80 / 100

Setup

Ready to use

License

MIT

Language

TypeScript

Install

Quick start

Copy the command, or hand the whole task to your harness agent.

git clone https://github.com/thomasvvugt/dsh-kanban-flow.git
Install with your agent

Please install the DeepSeek Harness plugin "dsh-kanban-flow" for me. - GitHub repository: thomasvvugt/dsh-kanban-flow (https://github.com/thomasvvugt/dsh-kanban-flow) - Type: a Cordis plugin (installed into a DSH profile) - It should work out of the box with n…

From the README

A cleaned excerpt from the project's own documentation.

dsh-kanban-flow Agent-driven kanban boards for DeepSeek Harness — one board per workspace, one task session per item. You triage. The agent picks up, works, narrates every step in its own task session, and asks for review when it needs you. The board enforces the workflow — not vibes: agents can't grab unassigned work, can't skip your review, and can't close items behind your back. Partially based on the dsh-kanban plugin architecture, rebuilt around a multica-style human/agent workflow.…

Open on GitHub

Project details

by
thomasvvugt
License
MIT
stars
5
Forks
1
Updated
Sep 26, 2026
Created
Aug 25, 2026
Language
TypeScript
Indexed from
topic

Related entries

Similar tools from the same corner of the ecosystem.

View all
Plugin

dsh-synapse

liangmianya

A visual, non-linear conversation workspace plugin for DeepSeek Harness ; A canvas-based session explorer and branching workspace for DeepSeek Harness.

deepseekdeepseek-harnessdsh
703Ready to use
81/100
Plugin

dsh-kanban

alpacachen

A shared kanban board for people and AI agents in DeepSeek Harness.

ai-agentdeepseek-harnessdsh
23Ready to use
81/100
Plugin

dsh-multitask

Senguk520

A Multitask "shock absorber" plugin & agent preset for DeepSeek Harness (DSH): the main chat only plans, briefs subagents and summarizes results, while file reads, commands, search and builds all run inside subagent contexts. Four worker types, an approval gate, zero DSH source changes.

agent-presetcontext-engineeringcontext-management
52Ready to use
78/100