Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Multi-Model LLM Council

    1

    Make Claude, ChatGPT, Gemini, Kimi, GLM, DeepSeek, Qwen, Manus and your local Ollama models solve a problem together: blind peer review with a ranked vote, or an open debate until they reach consensus.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Multi-Model LLM Council

    Multi-Model LLM Council

    Example session with this skill installed

    Run a council with qwen and medgemma (my local Ollama models), review method: A bat and a ball cost 1.10 in total. The bat costs 1.00 more than the ball. How much does the ball cost? Answer briefly.

    • Read your context and instructions
    • Compiled the multi-model llm council

    Method: independent answers, then blind peer review and ranking. Members: qwen (Ollama CLI), medgemma (Ollama API). Saved to councils/<date>-a-bat-and-a-ball/report.md.

    Council answer (written by qwen, the top-ranked member)

    Final answer

    The ball costs 0.05.

    Where the council agreed

    Both members agreed on the final answer (0.05) and the algebra behind it. Both identified that the intuitive answer of 0.10 fails the condition: if the ball cost 0.10, the bat would cost 1.10 and the total would be 1.20, not 1.10. Both reported high confidence.

    Where it disagreed, and how it was resolved

    The disagreement was about presentation, not the mathematics.

    • Response A gave a short derivation with one variable.
    • Response B gave a long step-by-step breakdown with assumptions, two variables and a check step.

    The peer vote ranked Response A higher because it followed the request to answer briefly. Both answers are correct.

    Remaining uncertainty

    None for the mathematics: the problem has a unique solution, assuming normal two-decimal currency.

    Peer ranking (Borda count)

    RankMemberPoints
    1qwen2
    2medgemma0

    Members' final answers

    qwen (Response A): Let b be the cost of the ball. The bat costs b + 1.00. Total: b + (b + 1.00) = 1.10, so 2b = 0.10 and b = 0.05. CONFIDENCE: high

    medgemma (Response B): A step-by-step breakdown (assumptions, variables x and y, two equations, substitution, check) reaching the same answer: the ball costs 0.05. CONFIDENCE: high

    Next steps

    • Add a cloud model (Claude, ChatGPT or Gemini) for a stronger council: council.py add claude --preset claude --via cli
    • Try the open debate method on a design question: council.py ask "..." --method consensus --rounds 3

    Connects securely to your tools. The creator never sees your data.

    About this skill

    One problem, many models, one answer you can trust more

    Ask a single model and you get a single point of view, with its blind spots. This skill turns the models you already have into a council that works on the same problem and checks each other's work.

    You choose everything

    • Which models sit on the council. Nothing is preset. Claude, ChatGPT/GPT, Gemini, Kimi (Moonshot), GLM (Z.ai), DeepSeek, Qwen, Mistral, Manus, OpenRouter, local Ollama and LM Studio models, opencode, or any other CLI or OpenAI-compatible server.
    • How each model is reached: through its API (your own key, read from an environment variable) or its CLI on your PC, using the login or subscription you already have (claude, codex, gemini, ollama, opencode...).
    • The method, for every run:
    MethodHow it worksBest for
    reviewEach model answers alone, then reviews the others' answers blind (anonymous, shuffled), revises, and ranks them (Borda count, no voting for yourself). The top-ranked model, or a chair you name, writes the synthesis.Checking work, finding errors, avoiding groupthink
    consensusThe models debate openly, in turn, editing one shared draft until every model accepts it, or the rounds run out. Holdouts are named.Design, planning, open-ended problems

    What you get

    • A final answer that says where the models agreed, where they disagreed, and what is still uncertain.
    • A readable report.md and a full transcript.json of every round, so you can audit the reasoning.
    • Claude in your current session can sit on the council too.

    Built to run unattended

    • Python standard library only: nothing to pip install.
    • A member that fails (bad key, quota, timeout) is reported and dropped; the council carries on.
    • doctor --ping checks that every member really answers before you spend money on a council.
    • API keys never go into files: only the name of the environment variable is stored.

    Honest limits

    Models can agree and still be wrong, and models trained on similar data share blind spots. The skill reports real dissent instead of smoothing it over, and tells you to check facts, numbers and citations.

    One-time purchase: install and use it in your own projects and your own team, with free updates when a new version is published.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires Python 3.9+ and at least 2 models: your own API keys and/or model CLIs installed and logged in on your PC. API calls cost money and CLI calls count against subscription limits; each extra round adds one call per model. Manus runs a full agent task per call, so it is slow and uses Manus credits. Models can agree and still be wrong: check facts, numbers and citations.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    Accounts
    OpenAIAnthropicGoogle AIManus
    Software
    Python 3.9+
    At least 2 models: API keys
    orinstalled model CLIs

    Each model you add is reached through its API (your own key, set as an environment variable) or its CLI (your existing login). API calls cost money; CLI calls count against your subscription.

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    api.openai.com
    api.anthropic.com
    generativelanguage.googleapis.com
    api.manus.ai

    File Scopes

    council.json
    councils/**

    Terminal: runs the bundled Python script and the model CLIs you choose. Network: calls the APIs of the models you add. Environment variables: reads your API keys (only the variable names are stored, never the keys). Write files: saves council.json and the reports in councils/. The services listed are examples; you connect only the models you choose.

    Listed6 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    In review mode every model answers alone first, then reviews the others' answers anonymously and in shuffled order, so no model defers to a big name. Rankings are combined with a Borda count, and a model's vote for its own answer is not counted. The final report shows where the models agreed and disagreed. This reduces single-model blind spots, but models trained on similar data can still share mistakes, so check important facts yourself.

    Presets cover Claude, ChatGPT/GPT, Gemini, Kimi, GLM (Z.ai), DeepSeek, Qwen, Mistral, Manus, OpenRouter, Ollama, LM Studio and opencode. Each is reached through its API (your own key) or its CLI (claude, codex, gemini, ollama, opencode). Any other OpenAI-compatible server or command-line program can be added too. Manus is reached through its task API.

    A one-time purchase gives you the complete skill: SKILL.md (the workflow your agent follows), presets.json and council.py, a single Python script with commands to add models, check them, and run a council, plus updates when new versions are published. You may use and modify it for yourself and your own organisation, but not redistribute it. The models themselves are paid by you: API usage on your own keys, or your existing CLI subscriptions.

    Yes. Run council.py doctor --ping: it sends a one-word test to every member and reports which ones answer, with the exact fix for any that do not (set a key, install a CLI, or log in). council.py presets lists every model that can be added and whether it runs through an API or a CLI.

    Only for the models you reach through their API: each one uses your own key, set as an environment variable (only the variable name is stored, never the key). Models reached through their CLI (claude, codex, gemini, ollama, opencode) use the login you already have, and local Ollama or LM Studio models need no key. Each round makes one call per model, so more rounds cost more.

    Each council is saved to councils/<date>-<topic>/: report.md gives the final answer, where the models agreed and disagreed, what is still uncertain, the peer ranking (review) or the consensus status and holdouts (consensus), and every model's final answer. transcript.json keeps every round in full.

    New in Agents & Orchestration