Mylukin Agent Council
mylukin-agent-council is a Claude Code plugin for the Validate phase that runs a multi-model CLI council so Claude, Codex, and Gemini can produce consensus-driven decisions.
by mylukin · github.com/mylukin/agent-council
Install when you want a CLI that runs Claude, Codex, and Gemini together and surfaces a consensus decision instead of trusting one model.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install mylukin-agent-council@mylukin/agent-councilBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:mylukin/agent-council") and the paste-ready config with skillselion.get_install_config("plugin:mylukin/agent-council").
What it does
mylukin-agent-council is a Claude Code plugin that packages a multi-model AI council CLI. Solo builders use it when a decision matters—feature scope, technical direction, or risk—and they want more than one frontier model in the loop. The tool is described as driving consensus-driven outcomes across Claude, Codex, and Gemini rather than treating any single answer as final. That makes it a decision layer on top of your existing agents, not a replacement for coding skills or MCP integrations. It fits indie workflows where you cannot afford a review committee but still want disagreement surfaced before you ship. Install it when you already run multiple model providers and want a repeatable CLI ritual for hard calls. Complexity is intermediate because you must configure and trust several APIs and interpret synthesized consensus. It is less about daily autocomplete and more about de-risking commitments during validate and build.
Highlights
- Multi-model AI council CLI combining Claude, Codex, and Gemini in one workflow
- Consensus-driven decisions instead of a single agent reply
- Terminal-first fit for builders already on Claude Code and Codex
- Community plugin bundle with 1 plugin in the mylukin/agent-council repo
- Oriented toward agent-assisted judgment calls, not file editing inside the IDE
Why builders use it
Solo builders often make irreversible calls based on one model’s confident wrong answer with no second opinion in the terminal.
After you add the plugin, you can invoke a council workflow that weighs multiple models and returns a clearer consensus-backed decision before you build or ship.
At a glance
- Type - Plugin in AI Agents.
- Adoption - 0 installs, 25 stars, 0 votes.
FAQ
Who is mylukin-agent-council for?
It is for solo and small-team builders who run several AI coding agents and want consensus-backed CLI decisions instead of one model’s solo judgment.
When should I use mylukin-agent-council?
Use it when you are scoping work, choosing between architectures, or reviewing a risky change and need Claude, Codex, and Gemini aligned or clearly disagreed before you commit.
How do I add mylukin-agent-council to my agent?
Register the mylukin/agent-council Claude Code plugin from the catalog, complete plugin setup for the council CLI, and invoke it from your terminal alongside your existing Claude Code sessions.
Comments
Share how you use mylukin-agent-council, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.