multi-model-orchestrator
v0.7.21Route software tasks across current Claude, GPT-5.6/GPT-6, and Grok 4.5 models with task-sized reasoning and independent review
By Andre PaatLicense: MIT0 GitHub starsUpdated last week
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 5 skill or MCP entries
- Source updated
- Sep 13, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install multi-model-orchestrator for Codex and Claude Code
codex plugin marketplace add paat/claude-plugins
codex plugin marketplace upgrade paat-plugins
codex plugin add multi-model-orchestrator@paat-pluginsPaste and run these commands in a terminal with Codex. They add and refresh the paat-plugins catalog, then install this plugin.
Compatibility: the page URL and API slug “multi-model-orchestrator” remain stable.
- Codex:
multi-model-orchestrator@agent-plugin-marketplace→multi-model-orchestrator@paat-plugins
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/paat/claude-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/multi-model-orchestrator/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/meta-orchestration/SKILL.md├── skills/multi-model-orchestration/SKILL.md├── skills/multi-model-orchestrator-meta-orchestrate-workflow/SKILL.md├── skills/multi-model-orchestrator-orchestrate-workflow/SKILL.md└── skills/route-model-task/SKILL.md
Included Skills5
Use when running the show over a queue of work — an epic, an issue list, a discovery goal, or a workitem scan — through multi-model worker and reviewer legs with adversarial gates, crash-safe handoffs, and tribunal close-out. Entrypoint: /multi-model-orchestrator:meta-orchestrate.
Use when a user asks to implement through Claude Code, Codex, or Grok Build workers with task-appropriate model and reasoning selection plus independent review.
Run /multi-model-orchestrator:meta-orchestrate workflow from multi-model-orchestrator.
Run /multi-model-orchestrator:orchestrate workflow from multi-model-orchestrator.
Choose a Claude Code, Codex, or Grok Build model and reasoning effort for implementation, planning, investigation, review, or verification. Use when an orchestrator must assign tasks, when the user asks which coding model or effort to use, or when provider restrictions, latency, cost, risk, or independent-review needs affect routing.
Plugin manifests2
{
"name": "multi-model-orchestrator",
"version": "0.7.21",
"description": "Route software tasks across current Claude, GPT-5.6/GPT-6, and Grok 4.5 models with task-sized reasoning and independent review",
"author": {
"name": "Andre Paat"
},
"interface": {
"displayName": "Multi Model Orchestrator",
"shortDescription": "Route software tasks across current Claude, GPT-5.6/GPT-6, and Grok 4.5 models with task-sized reasoning and independent review",
"longDescription": "Route software tasks across current Claude, GPT-5.6/GPT-6, and Grok 4.5 models with task-sized reasoning and independent review",
"developerName": "Andre Paat",
"category": "Development",
"capabilities": [
"Skills",
"Scripts"
],
"defaultPrompt": "Use the multi-model-orchestrator plugin for this task.",
"websiteURL": "https://github.com/paat/claude-plugins"
},
"homepage": "https://github.com/paat/claude-plugins",
"repository": "https://github.com/paat/claude-plugins",
"license": "MIT",
"keywords": [
"orchestration",
"codex",
"claude",
"opus",
"grok",
"gpt-5.6",
"gpt-6",
"subagents",
"code-review",
"epic"
],
"skills": "./skills/"
}{
"name": "multi-model-orchestrator",
"version": "0.7.21",
"description": "Route software tasks across current Claude, GPT-5.6/GPT-6, and Grok 4.5 models with task-sized reasoning and independent review",
"author": {
"name": "Andre Paat"
},
"repository": "https://github.com/paat/claude-plugins",
"license": "MIT",
"keywords": [
"orchestration",
"codex",
"claude",
"opus",
"grok",
"gpt-5.6",
"gpt-6",
"subagents",
"code-review",
"epic"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[multi-model-orchestrator on Agent Plugins Marketplace](https://pluginsmp.com/plugins/multi-model-orchestrator)