DSH Plugin | Workflow Automation for DeepSeek Harness Plugin
Free Workflow & Automation DSH Plugin for DeepSeek Harness: browse, search, download, install task orchestration, scheduling. Verified, traceable sources.

DSH Plugin Hub is a community plugin marketplace for DeepSeek Harness (DSH plugin), built to the official plugin spec and embedded in Settings → Plugin Market. Browse, search and one-click install human-curated community plugins without leaving the app, synced daily with dsh-plugin.org.

DSH Taskboard is a native local taskboard plugin for DeepSeek Harness, using SQLite for project/task management with Agent claim/review, a native Web UI, and a CLI.

A local creator workbench for DeepSeek Harness, organizing each video's topic, script, subtitles, covers and publishing status into one folder with AI-assisted workflow.

DSH Workflow brings a durable, governable, observable, and resumable workflow layer to DeepSeek Harness, turning one-shot multi-agent orchestration into reusable engineering assets.

DSH plugin that runs coding tasks on schedule in fresh Agent sessions, with schedule management from DSH Web or an Agent, leaving auditable run history.

A DSH plugin delivering an AI recruiting workflow for HR/headhunters: role profiling, dual-channel sourcing, resume screening, interview scheduling, tracking and daily reports, with an operable recruiting browser panel.

DSH plugin approval gate: Flash predicts sandbox escapes, auto-approves safe actions, escalates risky ones to human review, with confirmation-based learning and UI review.

DeepSeek Flow is a visual, Markdown-first workflow editor for DeepSeek Harness, offering canvas editing, two-way sync, and AI assistance for portable workflow design.

dsh-taskboard adds a task board to DeepSeek Harness: humans create cards, agents claim and execute, humans review, with cron scheduling and Git Worktree isolation.

A visual multi-agent workflow orchestration plugin for DeepSeek Harness, enabling drag-and-drop flow design with dual-mode execution, checkpoint resume, and real-time editing.

A DSH plugin that turns DeepSeek Harness into a personal workbench with calendar, hierarchical tasks, and AI-assisted clarify/decompose/execute/review workflow.

A DSH plugin — the management kernel for multi-agent pipelines: task board, ledger, deployment, registry, watchdog, packaging & reuse; pipeline-agnostic and user-defined.

DSH Automation is a DeepSeek Harness plugin that schedules and manages coding tasks in isolated sessions, supporting various schedules and run history.

dsh-approve-for-me is a DeepSeek Harness plugin for rule-gated automatic approval of Shell/PowerShell sandbox escalations, with optional LLM review, one-time grants, fixed high-risk checks, and native human fallback.

Ramify is a creative branching canvas plugin for DeepSeek Harness, enabling generation, comparison, and iteration of multiple interactive ideas in a tree workspace.

Integrates Codex as a conversation backend into DeepSeek Harness, enabling native Codex conversations in the DSH Web UI with workspace, terminal, approval, and DSH tool support.

A DSH plugin that audits your machine: live port inspection with one-click safe release, plus CLI toolchain versions, model credential presence and loaded DSH plugins.

dsh-kanban provides a shared kanban board for DeepSeek Harness, letting you and your AI agent plan, organize, and ship work together without leaving DSH.

A DSH plugin: host-resident scheduled-jobs engine that fires real agent sessions via cron, supporting pinned sessions, project workdir, and default workspace, with timer_agent tool and web panel.

A DSH plugin for anchored plan annotations, turning binary plan approval into precise multi-comment reviews with structured feedback to the Agent.
How to pick a trustworthy Workflow & Automation DSH plugin
A Workflow & Automation DSH plugin turns repetitive tasks into automated pipelines — task orchestration, scheduling, approval policy and automated triggers that move DSH from a toolbox to operational automation. Check orchestration capabilities, approval and fault-tolerance mechanisms, and compatibility status so the flow can be trusted to run on its own.
- Orchestration: whether it supports conditional branches, loops, parallel tasks and human-in-the-loop steps that cover your real business flow.
- Approval and fault tolerance: whether critical steps require human approval and failures auto-retry or roll back — this determines reliability.
- Compatibility status: workflow plugins depend on DSH's task-scheduling interfaces — prefer verified plugins whose dshTarget matches to avoid scheduling breakage.
Where Workflow & Automation sits in the DSH taxonomy
Workflow & Automation is one of the eleven primary DeepSeek Harness categories, orchestrating discrete capabilities into continuously running flows: task orchestration, scheduling, approval policy and automated triggers. It complements Skills & Agents — skills define how a single task is done, workflows define how tasks chain together, when they trigger and who decides. It is the category that moves DSH from a toolbox to operational automation.
「Every part of the product is a plugin — including the model adapter, the tool registry, the session log, and the agent loop itself.」
SourcesOfficial site·Architecture docs·Repository
Related Terms
- Workflow & Automation DSH Plugin
- A Workflow & Automation DSH Plugin orchestrates DeepSeek Harness automation — task orchestration, scheduled runs, approval flows, automated reports and retry on failure.— DeepSeek Harness architecture docs
- Task orchestration
- Task orchestration is a workflow plugin's ordering of multi-step tasks by dependency — sequencing, parallel branches and output passing — turning scattered steps into a pipeline.— DeepSeek Harness architecture docs
- Scheduled runs
- Scheduled runs are a workflow plugin's time-based triggering — cron expressions and frequency configs that run routine tasks automatically.— DeepSeek Harness architecture docs
- Retry on failure
- Retry on failure is a workflow plugin's automatic rerun or fallback when a step fails — with retry counts, backoff and failure alerts — improving pipeline stability.— DeepSeek Harness architecture docs