DeepSeek Harness PluginIndexed

mstar-harness

Omni-plugin workflow engine providing multi-agent orchestration, audit tools, and programmatic quality gates for DeepSeek Harness.

UI & ProductivityTerminal & TUIDeveloper ToolsSecurity & PolicySkills & Workflows

65GitHub Stars4ForksUpdated2026-10-20

Source Homepage

Install

$ - Native: dsh plugin --profile web add @mstar-harness/dsh

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded

Morning Star (mstar-harness) is an engineering workflow platform and omni-plugin designed for DeepSeek Harness and other AI coding hosts. It orchestrates a structured software delivery lifecycle through dedicated agents—including project managers, architects, developers, and QC specialists—driving tasks from initial requirements and feature branch implementation to multi-seat QC reviews, pull requests, and verified merges.

Key Capabilities

Multi-agent role orchestration featuring project-manager, architect, developer, QA, and QC specialist seats
Comprehensive iteration workflow lifecycle commands (/iteration-start, /iteration-drive, and /iteration-loop)
Independent multi-seat pull request review and verdict scoring (/amazing-pr-review)
Read-only codebase and test surface audit tools (/codebase-audit, /amazing-test-audit)
Localhost read-only web dashboard for project workflows, issues, and roadmap visibility
Built-in Model Context Protocol (MCP) stdio server interface

Useful For

Managing complex, multi-step engineering tasks across feature branches with dedicated agent roles
Running automated multi-agent code audits, test surface analysis, and pre-merge pull request reviews
Tracking plan execution, issue lifecycles, and audit findings within local repository state

Who It Fits

Software engineers using DeepSeek Harness who require structured multi-agent workflows
Engineering leads seeking programmatic quality gates, audits, and formal review evidence before PR merge

Documented Limitations

Requires Node.js 24+ for prerequisites
MCP integration in DeepSeek Harness requires adding @deepseek-ai/dsh-mcp-client to the active profile
Workflow checks and gates are advisory by default unless configured to blocking enforcement
Audits and reviews do not perform automated merges or modify external environments without explicit authorization

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 1 runtime, 13 development, 0 peer, and 0 optional dependencies.

info

License Declared

GitHub reports the repository license as MIT.

info

Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info

Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository: btspoony/mstar-harness
Registry source: GitHub · dsh-plugin topic
Registry classification: Plugin Bundle
Source checked: d58005d · 2026-10-20

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.