DSH Marketplace
中文

dsh-automation

titanwings/dsh-automation

Scheduled coding runs in fresh agent sessions with auditable history.

514TypeScriptMITSource

Install

Add dsh-automation to DeepSeek Harness

via GitHub · GitHub source

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

What happened when we ran it

Installed cleanly when we ran it

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 2d ago.

Due diligence

Before you install dsh-automation

  • Source of record: titanwings/dsh-automation — present in the community registry that DSH's own plugin market installs from.
  • Licensed under MIT.
  • Detected: terminal surface. Read the source before granting these.
  • A listing here is not a security review. Plugins run with your agent's permissions.

The AI take

What it is — dsh-automation runs self-contained coding tasks on schedule in fresh agent sessions, leaving an auditable run history.

Who it is for — If you need to run recurring or one-shot coding work later without relying on old chat, each in an explicit workspace with permission boundary and inspect the history, dsh-automation fits. For tasks that depend on interactive approval midway through or react to file, HTTP, or process conditions rather than time, users do not need it as it targets time-based standalone executions.

Watch out — Installation from source requires Node.js 22.19 or newer. Sandbox test passed in fresh profile with harness registration. No obvious issues found.

The verdict — I would install it because sandbox tests confirm it runs in fresh sessions with auditable history for standalone coding tasks.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What dsh-automation does

Clock-marked task capsules enter fresh isolated agents through permission gates and settle into archival blocks.

dsh-automation is a DeepSeek Harness plugin that runs self-contained coding tasks on a schedule in fresh agent sessions and keeps durable run records. A schedule can be one-shot, fixed-interval, daily, or weekly; daily and weekly rules use an IANA time zone and are stored as validated RFC 5545 RRULE data. Each occurrence creates a new root Agent and Session rather than returning to an existing conversation.

DeepSeek Harness provides the Web Automations tab and six workspace-scoped agent tools for creating, listing, updating, pausing, resuming, running, and deleting automation definitions. A run uses the saved prompt, captured workspace, cwd, Agent preset, model target, and permission preset. The plugin writes definition revisions and run history containing the scheduled time, target snapshot, result Session ID, bounded summary, terminal status, and structured error. Set archiveRunSessions: true in the Cordis plugin config to archive terminal run Sessions; the default is false.

This is intended for recurring or one-off standalone coding work that can run without unstated chat history or mid-run approval. It is not a replacement for DeepSeek Harness Schedule when a reminder should return to the same live conversation, and it is unsuitable for tasks triggered by file, HTTP, or process conditions. The plugin reaches the terminal through the dispatched coding agent, within the selected workspace and permission boundary, so its activity depends on that agent's permissions.

dsh-automation documentation

How dsh-automation behaves

DeepSeek Harness dispatches each scheduled occurrence into a new root Agent and a new Session. The dispatched input is the saved prompt, not the source conversation history. The run also receives the captured workspace, cwd, Agent preset, model target, permission preset, and an automation message source containing the automation ID, run ID, and scheduled time. The terminal result comes from the actual DSH turn end.

Schedules support one-shot, fixed-interval, daily, and weekly rules. Daily and weekly schedules use an IANA time zone and are normalised to a validated RFC 5545 RRULE. Runs move through queued and running to a terminal state such as succeeded, failed, skipped, or cancelled.

Configuring dsh-automation

Set the following Cordis plugin option when completed run Sessions should be archived from the ordinary DeepSeek Harness conversation list:

Key Default Effect
archiveRunSessions false Archives terminal run Sessions while retaining their logs and run-history records

Archived results retain the Session ID, summary, and error in Automations history. Current Harness releases do not expose an unarchive API, so an archived result is labelled rather than given a Session-open action. Retention removes only the oldest terminal records; queued and running records are not pruned. Updating a definition increments its revision, and retained runs identify the revision they executed. Deleting a definition does not immediately delete its run records.

Commands and management tools

DeepSeek Harness exposes the Automations conversation tab in the Web profile. An eligible root Agent can use workspace-scoped management tools, including automation_create, automation_list, automation_update, and the controls for running, pausing, resuming, and deleting automations. These operations apply only to the Agent's exact workspace.

Requirements and limits

The README requires Node.js 22.19 or newer. Install the GitHub bundle into the DeepSeek Harness web profile and restart dsh web. The task must be self-contained: work that depends on unstated chat history, interactive approval, or non-time conditions is outside this plugin's documented use.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to dsh-automation

dsh-agent-teams

NanmiCoder

491

AgentTeams multi-agent teams.

Installed cleanly when we ran it

npm packageTypeScript2d ago

AI review

dsh-agent-teams

What it is — Converts a DeepSeek Harness session into a multi-agent team with role assignment, dependency-aware tasks, and direct messaging.

Who it is for — When I need to break a complex goal into dependency-aware subtasks and coordinate multiple continuable sub-agents, I would use this plugin. Users who only need single-agent execution would not require it, as the plugin requires binding work to a single captain-led team.

Watch out — Sandbox testing confirmed successful registration and enabling in a fresh profile. No obvious issues were found. Team state is persisted in a file-backed directory, with no coordination for concurrent process edits to the same team.

The verdict — I would install it for persistent multi-agent coordination with automatic task claiming, but only if staying within single-team limits to avoid issues with concurrent process access.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

dsh-plugin

Tabbit-Browser

83

Tabbit Broser plugins for Deepseek Harness

Installed cleanly when we ran it

GitHub sourceJavaScript2d ago

AI review

dsh-plugin

What it is — The plugin provides Tabbit browser control capability for DeepSeek Harness.

Who it is for — When performing automation tasks with DeepSeek Harness that require browser integration, this plugin enables Tabbit control. It is not necessary if your DSH runs in a sandbox without local GUI Browser access, because this Skill does not make Tabbit automation available.

Watch out — Sandbox testing passed: installed in fresh profile and registered by harness. Static check indicates it can execute shell commands. From source install, the build script needs manual allowance first. Requires Tabbit browser version 1.9.0 or higher.

The verdict — I would install it because it handles Tabbit installation and Skill loading via background tasks, but only if local Tabbit GUI access is possible.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

dsh_workflow

icetomoyo

76

UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.

Installed cleanly when we ran it

GitHub sourceTypeScript6d ago

AI review

dsh_workflow

What it is — This plugin upgrades DeepSeek Harness one-time multi-agent scheduling into a generatable, savable, resumable workflow layer.

Who it is for — When running repeated complex multi-agent tasks like parallel investigations in DSH sessions, this plugin is suitable for saving workflows as reusable capsules. If your tasks are only brief one-time scheduling, this plugin's workflow layer is unnecessary because it focuses on higher-level flow product capabilities.

Watch out — Source installation requires manual approval of the build script. Sandbox test passed in a fresh profile and registered successfully. No obvious issues found.

The verdict — I would install it because it turns multi-agent into a long-term maintained agent workflow library.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

mstar-harness

btspoony

49

Skill-driven harness/loop engineering workflow agent plugin.

Installed cleanly when we ran it

GitHub sourceTypeScript2d ago

AI review

mstar-harness

What it is — Morning Star Harness is a TypeScript Harness Workflow Engine Agent Plugin that enforces deterministic workflow gates and provides mstar-* judgment skills.

Who it is for — When performing iteration or codebase audit in DeepSeek Harness for multi-agent code delivery, it fits. If your tasks do not involve judgment skills for engineering loops, you don't need to install it.

Watch out — From source install you need to manually whitelist the build script. It automatically executes scripts and runs shell commands. Sandbox test passed: installed in new profile and registered by harness, no obvious issues found.

The verdict — I would install it because it provides a portable engine across multiple hosts.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Details

agent_team_gui

toolclub

39

Reusable agent squads with per-agent provider/model routes and tool policies, serial/parallel dispatch, spawn/fork/chain context modes, and a Web management panel.

Installs, but needs a build approved first

GitHub sourceTypeScript2d ago

AI review

agent_team_gui

What it is — This plugin adds per-agent agent team support to DeepSeek Harness with independent model and tool policy configuration.

Who it is for — When handling multi-model agent collaboration tasks in the DeepSeek Harness web profile, this plugin supports per-agent model and tool policy selection. If you use a headless or bare-profile bundle, this plugin would not apply to your scenario.

Watch out — Sandbox testing shows the plugin can be installed but the build script requires manual approval to complete registration. No other issues found.

The verdict — I would install it because it supports per-agent model switching and persistent team saving, but I must manually allow the build script first.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

dsh-agent-team-gui

toolclub

39

Global persistent agent squads with per-agent model/tool policies: manage them in Settings, select and toggle one per conversation, then collaborate on normal sends in a fixed or model-planned order.

Installs, but needs a build approved first

GitHub sourceTypeScript2d ago

AI review

dsh-agent-team-gui

What it is — This plugin manages persistent agent squads in DeepSeek Harness. Each agent selects its own model and tool policy, and the user chooses and enables collaboration in the conversation.

Who it is for — It suits you when you need multi-agent collaboration with different models in DeepSeek Harness conversations. You don't need it if you only use a single agent.

Watch out — When installing from source, pnpm blocks the build script, requiring manual approval to register successfully. No other obvious issues found.

The verdict — I won't install it because of the need for manual approval of the build script, even though it supports persistent squad management.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source