Agent Plugins Marketplace
← All plugins

tribunal

v1.5.3

Multi-agent execution with LLM-as-a-Judge quality gates. An Actor performs work; a jury of typed Judges scores it against a project-overridable rubric; a Meta-Judge reviews the jury for bias; the gate decides accept, retry, or exhaust. Grounded in LLM-as-a-Judge (Zheng et al. 2023) and LLM-as-a-Meta-Judge (Wu et al. 2024). Builds on the Onlooker ecosystem plugin.

Claude Code1 Skill

By Onlooker CommunityLicense: MIT0 GitHub starsUpdated 4 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 20, 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 tribunal for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install tribunal@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

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/onlooker-community/ecosystem

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/tribunal/.

Plugin files

plugins/tribunal/
├── .claude-plugin/plugin.json
└── skills/tribunal/SKILL.md

Included Skills1

tribunalskills/tribunal/SKILL.md

Run a task under multi-agent quality gates. Spawns the tribunal-actor subagent, a jury of typed Judges, and a Meta-Judge; aggregates verdicts under a configurable gate policy; retries the Actor with critique on rejection until acceptance or max_iterations. Use when the user explicitly wraps a task with /tribunal, or wants stronger correctness/safety review than a single pass. Emits the full tribunal.* canonical event stream.

Plugin manifests1

plugins/tribunal/.claude-plugin/plugin.json
{
  "name": "tribunal",
  "version": "1.5.3",
  "description": "Multi-agent execution with LLM-as-a-Judge quality gates. An Actor performs work; a jury of typed Judges scores it against a project-overridable rubric; a Meta-Judge reviews the jury for bias; the gate decides accept, retry, or exhaust. Grounded in LLM-as-a-Judge (Zheng et al. 2023) and LLM-as-a-Meta-Judge (Wu et al. 2024). Builds on the Onlooker ecosystem plugin.",
  "author": {
    "name": "Onlooker Community",
    "url": "https://onlooker.dev"
  },
  "homepage": "https://onlooker.dev",
  "repository": "https://github.com/onlooker-community/ecosystem",
  "license": "MIT",
  "skills": [
    "./skills/tribunal"
  ],
  "agents": [
    "./agents/tribunal-actor.md",
    "./agents/tribunal-judge-standard.md",
    "./agents/tribunal-judge-security.md",
    "./agents/tribunal-judge-adversarial.md",
    "./agents/tribunal-meta-judge.md"
  ]
}

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.

[tribunal on Agent Plugins Marketplace](https://pluginsmp.com/plugins/tribunal)