DSH Marketplace

dsh-automation

titanwings/dsh-automation

Scheduled coding runs in fresh agent sessions with auditable history.

10112TypeScriptMITSource

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 14d ago.

Show it in your README

install verified — dshmarketplace

For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.

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 enables scheduling coding tasks in fresh root Agent sessions within DeepSeek Harness with auditable run history.

Who it is for — Developers needing recurring or one-shot coding work to run later without relying on an old chat are suitable for this plugin. Tasks that depend on unstated chat history, require interactive approval mid-way, or should react to file/HTTP/process conditions rather than time are not suitable.

Watch out — Sandbox testing passed: installed in a fresh profile and registered into Harness. It can execute shell commands, but no obvious issues were found.

The verdict — I would install it because it supports running tasks independently in fresh sessions with audit trails when unattended execution in explicit workspace is needed.

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

6.0k

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython14d ago

AI review

dsh-plugin

What it is — This DSH plugin mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DeepSeek Harness.

Who it is for — Users performing workflow tasks in DeepSeek Harness benefit from this plugin. People who do not need to mount external Agent OS via DSH MCP do not need this plugin.

Watch out — It is a subdirectory plugin with no single install command. It will execute shell commands. No sandbox testing was performed; no obvious pitfalls found.

The verdict — I would install it because it integrates Ouroboros directly for DeepSeek Harness.

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-loopx-plugin

loopx-project

6.0k

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython10d ago

AI review

dsh-loopx-plugin

What it is — The dsh-loopx-plugin provides a LoopX control plane for DeepSeek Harness, managing durable goals, todos, evidence, and handoffs for long-horizon agents.

Who it is for — When building coding or research agents with DeepSeek Harness that require cross-session Goal and Todo state, this plugin can be installed. For users who only need single-session instant task completion, the durable state management provided by this plugin falls outside their requirements.

Watch out — No obvious issues found. From source installation, the build script requires manual approval to execute.

The verdict — I would install it because it maintains a bounded loop GoalBar for DeepSeek Harness agents, which is necessary for long-horizon work.

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-loopx-plugin

huangruiteng

5.9k

LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourcePython13d ago

AI review

dsh-loopx-plugin

What it is — DeepSeek Harness plugin that bootstraps LoopX CLI and integrates skills.

Who it is for — For managing long-horizon agent tasks using DeepSeek Harness, it adds state management. Users running agent tasks on non-DeepSeek Harness frameworks won't need this plugin.

Watch out — No obvious issues identified. Static checks show it will execute shell commands. Sandbox testing has not been conducted.

The verdict — I would install it because it enables long-horizon state management on DeepSeek Harness, but only for tasks requiring bounded loop continuation.

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
3.2k

Embeds the active installed Codex Taskboard runtime in the DeepSeek Harness sidebar, using its launcher runtime descriptor instead of a fixed port.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceJavaScript15d ago

AI review

deepseek-harness

What it is — Integrates Codex Taskboard runtime into DeepSeek Harness sidebar.

Who it is for — Users who embed Codex Taskboard into DeepSeek Harness sidebar are suitable to install this plugin. Users who do not want to provide an API key or token are not suitable to install it, because it requires providing one.

Watch out — No sandbox testing was performed. It requires providing an API key or token and may execute shell commands. No obvious issues found.

The verdict — I would not install it because there is no single command to install it.

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
2Source

dsh-agent-teams

NanmiCoder

1.8k

AgentTeams multi-agent teams.

Installed cleanly when we ran it

npm packageJavaScript9d ago

AI review

dsh-agent-teams

What it is — Converts a DeepSeek Harness session into a captain-led multi-agent team.

Who it is for — When you need to break a goal into dependency-aware tasks and coordinate sub-agents through direct messages in a DeepSeek Harness session, if your work only involves a single agent without team coordination.

Watch out — Sandbox test passed: installed in a fresh profile and registered by harness. Static check shows it will execute shell commands. No obvious pitfalls found.

The verdict — I would install it because it provides all coordination tools and live UI in one session, but only if using a supported Harness version.

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
1.0k

TongFlow film-crew studio for image, voice, music and video production: the agent writes per-asset TongFlow workflow files (.tongflow.json) that run through TongFlow plugins, with an embedded workflow canvas, a shot/character/take project layout and a manga-drama template; sessions starting with @tongflow open the Studio view.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceTypeScript20d ago

AI review

dsh-tongflow

What it is — The dsh-tongflow plugin allows writing TongFlow workflow files in DeepSeek Harness.

Who it is for — When producing images, voice, music and video content in DeepSeek Harness, this plugin is suitable. If you do not want to use shot/character/take project layouts, you can choose other tools.

Watch out — The plugin will execute shell commands. No obvious pitfalls found.

The verdict — I would install it, but only if I need to use TongFlow plugins.

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