Hive Workers
npx machina-cli add skill smith-horn/product-builder-starter/hive-workers-skill --openclawHive Workers Skill
Orchestrates complex task execution using ruflo hive mind with automatic code review and documentation updates.
Quick Start
0. EXPLORE: Search codebase for existing implementations (MANDATORY)
1. Read the task or issue
2. Initialize hive mind: swarm_init({ topology: "hierarchical" })
3. Create todos: TodoWrite with all tasks
4. Execute in parallel where possible
5. Run code review with Task agent
6. Fix any "Must Fix" items
7. Run governance audit
8. Create ADR if architectural decision
9. Update project status
10. Generate sprint report
11. Cleanup: swarm_destroy, mark issues done
Execution
When triggered, immediately:
- Read
agent-prompt.mdfrom this skill's directory (./agent-prompt.md) - Spawn a single Task with
subagent_type: "general-purpose"passing the agent-prompt content as the prompt - Include in the prompt: the user's request, current working directory, and any arguments passed
- Wait for the agent to complete
- Present the agent's summary to the user
Sub-Documentation
| Document | Contents |
|---|---|
| agent-prompt.md | Full execution workflow, phase details, checklists |
| context-persistence.md | Maintaining context across sessions for long-running tasks |
| CHEATSHEET.md | Quick reference for common operations |
| templates/ | Workflow templates for task execution |
Related Skills
- governance - Standards enforcement
- worktree-manager - Parallel development
Prerequisites
- ruflo configured (
claude mcp add ruflo -- npx ruflo@v3alpha mcp start) - Linear MCP (optional, for issue tracking)
For full execution details, see agent-prompt.md.
Changelog
v1.0.0 (2026-03)
- Initial public release
- 11-step hive mind execution workflow
- ruflo MCP integration (
swarm_init,agent_spawn,task_orchestrate,swarm_destroy) - Automatic governance audit after execution
- Context persistence across sessions (
context-persistence.md) - Workflow templates for common task types
Source
git clone https://github.com/smith-horn/product-builder-starter/blob/main/skills/hive-workers-skill/SKILL.mdView on GitHub Overview
Hive Workers orchestrates complex task execution using a hive mind of parallel agents. It integrates automatic code review and documentation updates to keep code and docs in sync. This approach supports feature work, epics, or multi-task projects while adding governance and traceability.
How This Skill Works
On trigger, it reads agent-prompt.md and spawns a single Task with subagent_type: 'general-purpose', passing the user request, current working directory, and any arguments. The system executes tasks in parallel where possible, invoking the Task agent for automatic code review and addressing 'Must Fix' items. It then runs a governance audit, creates an ADR when needed, updates project status, and performs cleanup with swarm_destroy.
When to Use It
- Kick off a feature or epic that spans multiple modules and teams
- Parallelize independent tasks to accelerate delivery
- Require automatic code review and documentation updates as part of work
- Enforce governance checks and ADR creation after execution
- Wrap up and report sprint progress and project status
Quick Start
- Step 1: EXPLORE the codebase and read the task or issue (MANDATORY)
- Step 2: Initialize hive mind: swarm_init({ topology: "hierarchical" }) and create a TodoWrite with all tasks
- Step 3: Execute in parallel, run code review, fix issues, run governance audit, update ADR and status, then cleanup: swarm_destroy
Best Practices
- MANDATORY EXPLORE: Search for existing implementations before task creation
- Create a complete TodoWrite with all tasks to coordinate work
- Prefer parallel execution for independent tasks to maximize throughput
- Use the Task agent for automatic code review and to resolve 'Must Fix' items
- Run governance audits and capture ADRs; cleanup the swarm after completion
Example Use Cases
- Implement a new feature across frontend, API, and database with parallel tasks
- Deliver an epic including UI changes, backend refactor, and docs updates
- Migrate to a new logging library while updating ADR and docs
- Refactor a core module with automatic reviews and governance checks
- Coordinate a multi-team bug-fix sprint and generate a sprint report
Frequently Asked Questions
Related Skills
compose
chaterm/terminal-skills
Docker Compose įžæ
unified-review
athola/claude-night-market
'Use this skill when orchestrating multiple review types. Use when general
Plan Review
smith-horn/product-builder-starter
Multi-perspective plan review with VP Product, VP Engineering, and VP Design. Use when reviewing implementation plans, design docs, architecture proposals, or wave plans for blockers, anti-patterns, conflicts, and regressions.
flows
victorgrein/spec-crew
This skill should be used when designing CrewAI Flows with typed state management, deterministic routing, and event-driven orchestration. Use it for flow architecture, state transitions, control primitives, and production deployment.
