Model Council Pro

Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win...

Security Scan

The skill's code, runtime instructions, and requested environment variable (OPENROUTER_API_KEY) are consistent with a multi-model consensus tool that calls OpenRouter; nothing requests unrelated credentials or performs unexpected local file access.

Purpose & Capability

Name/description claim: send queries to multiple LLMs via OpenRouter and have a judge model pick/synthesize results. Declared requirement: OPENROUTER_API_KEY. The Python script calls openrouter.ai endpoints and implements parallel calls + a judge step. All required resources align with the stated purpose.

Instruction Scope

SKILL.md and the script only instruct the agent to call OpenRouter endpoints, aggregate responses, and have a judge model evaluate them. The code reads only the declared OPENROUTER_API_KEY env var, performs network calls to openrouter.ai, and prints or emits JSON results. It does not read arbitrary local files, other env vars, or reach out to unexpected third-party endpoints.

Install Mechanism

No install spec; this is an instruction-only skill with an included Python script. No external archives/downloads or package installs are performed by the skill itself, minimizing install-time risk.

Credentials

Only OPENROUTER_API_KEY is required and used. This is proportional: the key is needed to route queries to multiple models and will be used in Authorization headers. Note: the key grants the skill the ability to make API calls (and incur costs) on the user's OpenRouter account and may expose prompts/responses to OpenRouter's logs—this is expected for the stated purpose but is an important operational/privacy consideration.

Persistence & Privilege

always:false and default invocation settings are used. The skill does not persist or modify other skills or system configuration; it only performs runtime network calls. No elevated or persistent privileges are requested.

Assessment

This skill appears to do what it says: it uses your OPENROUTER_API_KEY to call OpenRouter and aggregate multiple model outputs. Before installing, consider: (1) Cost and billing — calls to multiple models (and a judge model) can incur non-trivial charges; monitor usage and set quotas. (2) Data exposure — prompts and model outputs are sent to OpenRouter and the upstream model providers and may be logged; avoid sending secrets or sensitive data. (3) Verify the OPENROUTER_API_KEY you provide has appropriate scope/limits and rotate keys if you later remove the skill. (4) If you need stricter privacy, confirm OpenRouter's logging/retention policy or run a trusted in-house routing endpoint. Overall the skill is coherent and consistent with its purpose; proceed if you accept the cost and data-exposure tradeoffs.

Model Council 🏛️

Get consensus from multiple AI models on any question.

Send your query to 3+ different LLMs simultaneously via OpenRouter. A judge model evaluates all responses and produces a winner, reasoning, and synthesized best answer.

When to Use

• Important decisions — Don't trust one model's opinion
• Code review — Get multiple perspectives on architecture choices
• Research verification — Cross-check facts across models
• Creative work — Compare writing styles and pick the best
• Debugging — When one model is stuck, others might see the issue

How It Works

Your Question
    ├──→ Claude Sonnet 4    ──→ Response A
    ├──→ GPT-4o             ──→ Response B
    └──→ Gemini 2.0 Flash   ──→ Response C
                                    │
                              Judge (Opus) evaluates all
                                    │
                              ├── Winner + Reasoning
                              ├── Synthesized Best Answer
                              └── Cost Breakdown

Quick Start

# Basic usage
python3 {baseDir}/scripts/model_council.py "What's the best database for a real-time analytics dashboard?"

# Custom models
python3 {baseDir}/scripts/model_council.py --models "anthropic/claude-sonnet-4,openai/gpt-4o,google/gemini-2.5-pro" "Your question"

# Custom judge
python3 {baseDir}/scripts/model_council.py --judge "openai/gpt-4o" "Your question"

# JSON output
python3 {baseDir}/scripts/model_council.py --json "Your question"

# Set max tokens per response
python3 {baseDir}/scripts/model_council.py --max-tokens 2000 "Your question"

Configuration

Flag	Default	Description
--models	claude-sonnet-4, gpt-4o, gemini-2.0-flash	Comma-separated model list
--judge	anthropic/claude-opus-4-6	Judge model
--max-tokens	1024	Max tokens per council member
--json	false	Output as JSON
--timeout	60	Timeout per model (seconds)

Environment

Requires OPENROUTER_API_KEY environment variable.

Output Example

═══ MODEL COUNCIL RESULTS ═══

Question: What's the best way to handle auth in a microservices architecture?

── Council Member Responses ──

🤖 anthropic/claude-sonnet-4 ($0.0043)
Use a centralized auth service with JWT tokens...

🤖 openai/gpt-4o ($0.0038)
Implement OAuth 2.0 with an API gateway...

🤖 google/gemini-2.0-flash-001 ($0.0012)
Consider using service mesh with mTLS...

── Judge Verdict (anthropic/claude-opus-4-6, $0.0125) ──

🏆 Winner: anthropic/claude-sonnet-4
Reasoning: Most comprehensive and practical approach...

📝 Synthesized Answer:
The best approach combines elements from all three...

💰 Total Cost: $0.0218

Credits

Built by M. Abidi | agxntsix.ai YouTube | GitHub Part of the AgxntSix Skill Suite for OpenClaw agents.

📅 Need help setting up OpenClaw for your business? Book a free consultation