openclaw-model-orchestratorMulti-LLM orchestration for OpenClaw with fan-out, pipeline, and consensus patterns. Dispatches tasks across 40+ models using AAHP v3 inspired handoffs.
Install via ClawdBot CLI:
clawdbot install homeofe/openclaw-model-orchestratorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/elvatis/openclaw-model-orchestrator.gitAI Analysis
The skill definition describes a legitimate multi-LLM orchestration tool with no direct evidence of credential harvesting, hidden instructions, or data exfiltration. The primary risks are indirect, stemming from the potential for unsafe shell commands (exec()) and calls to an external, user-provided Git repository, which could be manipulated to introduce malicious code at runtime.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
A development team uses the orchestrator to accelerate feature implementation. In fan-out mode, a planner decomposes a user story, workers code components in parallel, and a reviewer merges and refines the output, reducing time-to-market for new features.
A security firm employs consensus mode to assess vulnerabilities in a client's system. Multiple models analyze the same threat data, identifying overlapping risks and unique insights, which a reviewer synthesizes into a comprehensive audit report with prioritized recommendations.
A consulting agency uses pipeline mode to create detailed industry reports. A planner outlines research questions, workers gather and analyze data sequentially, and a reviewer polishes the final document, ensuring accuracy and professional presentation for client deliverables.
A media company leverages the orchestrator to produce high-quality articles. In fan-out mode, a planner generates topic ideas, workers draft sections concurrently, and a reviewer edits for coherence and style, streamlining content production across multiple platforms.
An e-learning platform uses the orchestrator to develop interactive courses. A planner structures the curriculum, workers create lesson materials and assessments in parallel, and a reviewer ensures alignment with learning objectives and accessibility standards.
Offer the orchestrator as a cloud-based service with tiered pricing based on usage volume, such as tokens processed or concurrent tasks. This model provides recurring revenue and scalability for enterprises needing frequent multi-model AI orchestration.
Sell annual licenses to large organizations for on-premises or private cloud deployment, including customization and dedicated support. This model targets industries with strict data privacy requirements, ensuring high-margin contracts and long-term client relationships.
Provide professional services to integrate the orchestrator into existing workflows, offering training, custom profile development, and optimization. This model generates revenue from project-based fees and ongoing maintenance contracts, catering to non-technical users.
💬 Integration Tip
Start by using the recommend command to auto-classify tasks and apply pre-configured profiles, then customize with specific models as needed to optimize performance and reduce token costs.
Scored Apr 19, 2026
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
A unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work mov...
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would improve response quality. Use this as a pre-processing step before answering complex questions.
Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or...