AI Agent Hub
Back to plugins
⚙️

dsh-maestro-meta

Workflow Updated 2026.09.14

Run the following command in DeepSeek Harness:

dsh plugin install ddtcorex/dsh-maestro-meta

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install ddtcorex/dsh-maestro-meta inside DeepSeek Harness to install this meta-bundle; the source lives at https://github.com/ddtcorex/dsh-maestro-meta

About this plugin

Setting up a full workflow inside the DSH / Maestro Harness ecosystem used to mean installing eight separate plugins one by one, aligning their versions by hand, and debugging peer-dependency conflicts repeatedly. dsh-maestro-meta collapses all of that into a single install: it ships zero runtime code and instead exposes a thin cordis.patch aggregation table that re-exports eight granular plugins, handing a new machine or CI runner the complete toolset in one step.

The eight aggregated surfaces each cover a distinct concern—a Cloudflare tunnel with remote proxy, PIN, and startup-notification trigger; a pluggable MR review pipeline (GitLab implemented, GitHub stubbed); Govard bridge tooling tailored for PHP, Magento, and Laravel projects; durable memory with five tracks, a todo list, and a confirmation queue; mobile drawer and sheet UI for DSH Web below the 1024 px breakpoint; a provider-neutral notification service with Telegram as the first channel; a shared settings store with a Settings card; and a dev-dashboard panel for the Maestro harness itself.

It is aimed at teams that have already adopted DeepSeek Harness for day-to-day engineering and want a one-shot setup on new workstations or CI runners, a single version pin to manage the entire toolset, and a clean boundary between the local umbrella workspace and the published artifact—without duplicating code.

Use Cases

  • Bootstrapping a new workstation with the full Maestro toolset in one step
  • Resolving all eight granular DSH plugin dependencies in a CI pipeline
  • Aligning and upgrading plugin versions across a team of developer machines

Best For

  • Development teams that rely on DeepSeek Harness as part of their daily workflow
  • Platform engineers responsible for CI/CD pipeline integrity and dependency alignment
  • Individual developers restoring a complete dev environment on a fresh machine