Workflow & Automation

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.

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.

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.

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.

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.

What it is — Adds an AI novel-writing preset and workbench to DeepSeek Harness.

Who it is for — Users who are writing long novels in DeepSeek Harness and want AI assistance for chapter generation with manual review are suitable for installing it. Users who require automated batch generation or integration with mature editors should not, as it only supports a minimal manual review workflow.

Watch out — No obvious issues found. This is an early MVP version with capabilities only about 10% of the desktop version. It only supports the minimal creation chain with manual approval.

The verdict — I would not install it, because it lacks the full project tree and batch workflows of the desktop version.

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.

What it is — Openwrite is a novel writing workbench plugin for DeepSeek Harness.

Who it is for — Users who are planning long novels in DeepSeek Harness and need to manage characters and outlines can use this plugin. Those who do not use DSH model configuration for review will find it inapplicable.

Watch out — Sandbox test passed. Installation and registration in a new profile ran smoothly. No obvious issues found.

The verdict — I would install it because it supports using a local Python backend to manage novel settings in DSH.

What it is — SandBase Harness connects to DeepSeek Harness over stdio MCP and provides a local runtime for managing agents and sessions.

Who it is for — When you need local sandboxed tool calling and persistent sessions it fits your use case. If you only rely on cloud-hosted models you do not need it.

Watch out — Source installation requires manually allowing the build script first. No other obvious issues found in testing.

The verdict — I would install it because it supports local infrastructure control and secure sandboxes, but I would have to manually handle the build step.

What it is — dsh-image-gen provides conversational image generation for DeepSeek Harness, letting the agent create and edit images directly in chat.

Who it is for — When using DeepSeek Harness to have the agent generate images from natural language descriptions in conversation. Users who pursue fully independent text-only workflows without any visual integration needs.

Watch out — Sandbox testing passed with no obvious issues. Requires API keys from various providers, potentially incurring costs based on usage limits.

The verdict — I would not install it because it relies on external provider image generation capabilities, which may be unstable or add extra costs in some scenarios.

What it is — Provides a local SQLite taskboard plugin for DeepSeek Harness to manage projects, tasks, comments, relations, attachments and workflow automation.

Who it is for — If you are using DeepSeek Harness web profile for project management needing local SQLite taskboard and taskboard_* agent tools for workflow automation. If you rely on Harness built-in tools or external task management systems, you don't need this plugin.

Watch out — Installation requires manually building and packing the plugin, which executes shell commands. Sandbox test passed in a fresh profile. No obvious issues found.

The verdict — I would install it because it restricts agent tools to only submitting to in_review, suitable for workflows needing human verification.

What it is — Provides reusable agent squads with per-agent model and tool policies, plus a Web management panel for planning and dispatching.

Who it is for — Suitable when you need planner, implementer and reviewer roles with different models assigned to each. Not for users seeking a single-model setup without team coordination overhead.

Watch out — Real-world install requires manually allowing the GitHub build script to bypass pnpm restrictions. No other issues observed in sandbox testing.

The verdict — I would install it because the team-based dispatch and per-member routing deliver more control than a solo agent, provided you handle the one-time build allowance.

What it is — Configure persistent multi-model teams supporting member model and tool policies.

Who it is for — Users who need multi-model collaboration for complex tasks using planner and reviewer models are suitable for this. Users who do not require dynamic workflow planning can skip this plugin.

Watch out — Sandbox test shows it can be installed but pnpm blocks the build script for github:toolclub/dsh-agent-team-gui. Users need to manually allow the build to register properly. No other obvious issues found.

The verdict — If I were to install it, I would use the compiled release package to avoid build issues, but still need to manually allow the build script for source installation.

What it is — dsh-research-report provides a verifiable research report engine for DeepSeek Harness with content-addressed evidence ledger and byte-level claim verification.

Who it is for — Researchers building evidence-bound reports in DeepSeek Harness would find this plugin suitable. Users not generating research claims can opt for non-verifiable reporting solutions.

Watch out — Sandbox testing passed on a fresh profile with Harness registration. No obvious issues found. It is compatible with Node ^22.19.0 || >=24.0.0 and peer dependencies at 0.1.1-rc.2.

The verdict — I would not install it because the peer dependencies are pinned to a fixed version, reducing flexibility across setups.

What it is — Integrates ego-lite browser into DeepSeek Harness with 32 structured ego_* tools and real-time observation window.

Who it is for — When an AI agent needs to log into authenticated websites, handle forms and provide real-time visibility of its actions using DeepSeek Harness, this plugin fits. If only command-line browser task execution without a graphical observation window is needed, this plugin is unnecessary.

Watch out — Tested successfully in a new profile where it was registered by harness. No obvious issues found.

The verdict — I would install it because it provides self-observation making the agent operate DSH interface visibly and under direct control.

What it is — ego-browser integrates ego-lite browser into DeepSeek Harness, providing 32 structured ego_* tools.

Who it is for — When an agent needs to perform web operations, form filling, or data extraction using DeepSeek Harness, this plugin is suitable. Users whose tasks are purely text processing or command execution can choose other plugins.

Watch out — Sandbox testing passed: installed in a fresh profile and registered with the harness. No obvious issues found in static checks.

The verdict — I would install it because it enables real-time observation of the agent and direct control over the browser, with self-observation allowing the agent to operate the DSH interface itself.

What it is — dsh-lowtide is a DeepSeek Harness plugin that automatically runs task batches in off-peak hours.

Who it is for — A user working with DeepSeek Harness agents on tasks who wants to automatically run them in off-peak hours fits installing dsh-lowtide. People who prefer no machine intervention in task release can skip it since every task must be manually released by hand.

Watch out — The plugin will execute shell commands. No sandbox testing has been performed. No obvious pitfalls found.

The verdict — I would install it because it provides a single build artifact that serves both desktop and web versions of DeepSeek Harness.

What it is — DeepSeek Harness plugin for queuing tasks in busy hours and running them automatically in off-peak windows.

Who it is for — Developers using DeepSeek Harness for multi-round agent tasks to save on peak pricing by running overnight. Those needing real-time interaction may not find it suitable because it maintains human control through manual queue releases.

Watch out — Requires manual permission for the build script from source installation. It executes shell commands. No obvious issues found.

The verdict — I would install it because it allows batch execution during valley pricing to reduce costs, provided I manage the manual queue releases.

What it is — DSH Crew plugin lets DeepSeek Harness agents dispatch work from Claude Code or Codex while keeping native subagent progress UI.

Who it is for — When handling multi-step AI agent tasks in Claude Code, DSH Crew plugin fits dispatching to DSH agents as subagents. Users of Grok do not need it, as they have no need for external tool integration.

Watch out — Sandbox tested through: successfully installed and registered in a fresh profile. Executes shell commands. No obvious issues found.

The verdict — I would install it because it adds native progress UI and vision bridging, but only if the workflow involves external tool dispatching.

What it is — Upgrade DeepSeek Harness one-time multi-agent scheduling to a generatable, savable, governable, observable, resumable workflow layer.

Who it is for — Suitable for users managing persistent tracking in DeepSeek Harness multi-agent workflows. Not suitable for users in permission-sensitive environments requiring manual build script approval, because source installation needs manual allowance of the build script.

Watch out — Installation requires GitHub source and manual build script approval. Sandbox test passes: registers into profile in fresh setup. Executes shell commands.

The verdict — I would install it when persistent tracking is needed, because it upgrades one-time scheduling to resumable workflow.

What it is — The DSH Workflow plugin upgrades DeepSeek Harness multi-agent scheduling to a generatable, savable, governable, observable, resumable workflow layer.

Who it is for — When you need to create reusable workflow templates supporting governance, pause and resume, this plugin applies. Users who only perform simple parallel tasks without needing governance or persistence can opt not to install it.

Watch out — Sandbox testing passed with successful installation and registration in a fresh profile. Static checks note that it will execute shell commands, but no obvious issues found.

The verdict — I would install it because it transforms multi-agent flows into maintainable engineering assets with governance and observability.

What it is — odai-dsh-plugin is a DeepSeek Harness governance and routing plugin compatible with DSH 0.1.1-rc.2.

Who it is for — If you need profile-wide governance in DeepSeek Harness, you can install odai-dsh-plugin. If you prioritize avoiding shell command execution, you may not need it because it will execute shell commands.

Watch out — Sandbox testing has not been done. No obvious pitfalls found. The static check indicates it will execute shell commands.

The verdict — I would install it because it supports profile-wide governance but only if your work requires routing and memory management.

What it is — This DSH Web plugin intercepts Enter in the input box and has another AI rewrite the message into a command for the work AI.

Who it is for — When using models like DeepSeek-V4.1-Flash that are heavily affected by prompt wording on tasks needing precise intent transmission, this provides structured command output. Users not using the DSH Web platform do not need this plugin either.

Watch out — Sandbox testing passed with no obvious issues. The static scan warning about executing shell commands is not a defect in practice.

The verdict — I would install it because it enables independent prompt optimization with automatic difficulty-based structuring of commands.