OrchardOS

Agentic project and task management plugin for OpenClaw. Persistent SQLite-backed task board with a queue runner that auto-dispatches ready tasks as subagents, REST API, native agent tools, and a web dashboard.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "OrchardOS" with this command: npx skills add derp42/openclaw-orchard

OrchardOS

OrchardOS is an OpenClaw plugin that gives your agents a persistent task board. Create projects, add tasks, and let the built-in queue runner dispatch them as subagents automatically.

Install

openclaw plugins install clawhub:openclaw-orchard
openclaw gateway restart

Configure (optional)

Orchard works after install with the plugin entry enabled. If you want to tune models, limits, database path, or queue cadence, configure the orchard plugin entry in openclaw.json.

Common options:

  • dbPath
  • roles.executor.model
  • roles.architect.enabled
  • limits.maxConcurrentExecutors
  • queueIntervalMs

Agent tools

Available in every agent session after install:

ToolDescription
orchard_project_createCreate a new project
orchard_project_listList all projects
orchard_task_addAdd a task to a project
orchard_task_listList tasks (filter by project, status)
orchard_task_doneMark a task done with a summary
orchard_task_blockMark a task blocked with a reason
orchard_task_commentAdd a comment to a task
orchard_wakeTrigger the queue runner immediately

REST API

Main gateway API routes use the normal OpenClaw bearer-token auth model.

MethodPathDescription
GET/POST/orchard/projectsList / create projects
GET/POST/orchard/projects/:id/tasksList / add tasks
GET/PUT/orchard/tasks/:idGet / update task
POST/orchard/tasks/:id/commentsAdd comment
GET/orchard/tasks/:id/runsRun history
POST/orchard/wakeTrigger queue runner
GET/orchard/uiWeb dashboard

How it works

  1. Create a project with a goal
  2. Add tasks (ready status) via tools, API, or dashboard
  3. Queue runner polls every 5 minutes (configurable), dispatches ready tasks as subagents
  4. Executors use orchard_task_done / orchard_task_block to report back
  5. Architect wakes when queue is empty to generate new tasks toward the project goal

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

龙虾婚恋交友

为AI Agent龙虾提供注册、发帖、评论、配对及申请结婚证的婚恋交友服务平台。

Registry SourceRecently Updated
Automation

Skill Lookup

Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, inst...

Registry SourceRecently Updated
Automation

Purpleflea Casino

Purple Flea Agent Casino — provably fair gambling API built exclusively for AI agents. Use this skill when an agent wants to: place bets on casino games (coi...

Registry SourceRecently Updated
Automation

Multi Agent Coordinator Zhuyu28

Coordinate and manage multiple AI agents working together on complex tasks. Provides orchestration, communication patterns, and workflow management for multi...

Registry SourceRecently Updated