DeepSeek Harness PluginManifest Valid

dsh-expert-orchestrator

Multi-agent orchestration agent preset for DeepSeek Harness featuring PM triage, expert delegation, DAG taskboards, and gated delivery.

Developer ToolsSecurity & PolicySkills & Workflows

4GitHub Stars0ForksUpdated2026-10-23

Source

Install

$ dsh plugin --profile web add github:mario841859784/dsh-expert-orchestrator

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

DSH Expert Orchestrator is an agent preset plugin for DeepSeek Harness that implements a structured multi-agent coordination lifecycle. It enforces a PM-first triage and planning phase, delegates implementation tasks to domain experts from bundled or downloadable rosters via summon tools, tracks execution using a zero-dependency DAG taskboard and mailbox message bus, and gates delivery through independent code reviews.

Key Capabilities

Per-turn request triage and five-anchor self-check to prevent task drift
PM-first decomposition, dependency mapping, and acceptance criteria formulation
Delegated execution using merged expert rosters via list_experts and summon_expert tools
Zero-dependency Python DAG task scheduler and file-based mailbox message bus
Independent reviewer gate and PM checkpoint before final commits
Continuous experience pooling capturing up to 3 reusable lessons per completed task
Support for custom experts, downloadable source packs, and persona layering

Useful For

Managing complex multi-step software development tasks without manual sub-agent micro-management
Running domain-specific development tasks requiring distinct planner, coder, and reviewer personas
Maintaining consistent project memory and engineering lessons across multiple agent execution turns

Who It Fits

DeepSeek Harness developers coordinating multi-step coding workflows
Software engineers wanting structured multi-agent task planning and validation gates
Teams requiring specialized sub-agent delegations and DAG-based task boards

Documented Limitations

Requires Python 3 on the host system to run taskboard.py and bus.py tools
Settings UI button for purging deleted custom experts is pending implementation
Upstream expert source packs must be fetched and verified separately after installation
Requires DeepSeek Harness engine version >=0.1.7-alpha.2 <0.2.0-0

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 0 runtime, 0 development, 1 peer, and 0 optional dependencies.

info

Dsh Bundle Declared

package.json declares DSH bundle metadata.

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: mario841859784/dsh-expert-orchestrator
Registry source: GitHub · dsh-plugin topic
Registry classification: Plugin
Source checked: c48db73 · 2026-10-24

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.