What makes Council Of Llms notable?

1.2K downloads. Trust evidence available

How should Council Of Llms be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Council Of Llms

Real multi-model council deliberation for OpenClaw subagents. Spawns 3 parallel subagents with different LLMs and distinct analytical perspectives (Strategy,... Skill: Council Of Llms Owner: wahajahmed010 Summary: Real multi-model council deliberation for OpenClaw subagents. Spawns 3 parallel subagents with different LLMs and distinct analytical perspectives (Strategy,... Tags: latest:2.0.0 Version history: v2.0.0 | 2026-05-14T12:31:30.186Z | user v2: Models are now user-configurable via council-config.json instead of hardcoded. Perspectives (Strategos/Analyticos/Creativos)

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

2.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 2.0.0release · observed May 14, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s173f134cjwrtga3tp1pwvjf8d851jc2:council-of-llms

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wahajahmed010-council-of-llms/snapshot"

Documentation

CLAWHUB

59,066 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: council-of-llms
description: "Real multi-model council deliberation for OpenClaw subagents. Spawns 3 parallel subagents with different LLMs and distinct analytical perspectives (Strategy, Analysis, Creativity), then synthesizes their independent outputs into a unified verdict with consensus points, disagreements, and action items. Fixes the single-model roleplay anti-pattern that causes context overflow and shallow analysis. Requires the subagent-orchestration skill for base spawning patterns. Triggers on: council, deliberate, debate, review, stress-test, multi-model, decision, verdict, analysis, perspectives."
tags:
  - council
  - multi-model
  - deliberation
  - analysis
  - decision-making
  - subagent
  - orchestration
  - llm
  - review
  - stress-test
---

# Council of LLMs

## Overview

A real council spawns **3 parallel subagents**, each with a different model and perspective, then synthesizes their outputs into a unified verdict. This is NOT one model roleplaying 3 experts — it's genuinely different models providing independent analysis.

## Models

Configure your council models in `~/.openclaw/council-config.json`:

```json
{
  "council_models": [
    "your-strategic-model",
    "your-analytical-model",
    "your-creative-model"
  ],
  "default_timeout": 900,
  "max_tokens": 8192
}
```

**Choose models with different strengths:**
- **Strategos (Strategic):** Pick a model known for strategic thinking, long-context reasoning, and business insight
- **Analyticos (Analytical):** Pick a model known for data analysis, technical precision, and logical reasoning
- **Creativos (Creative):** Pick a model known for creative thinking, novel perspectives, and user empathy

The more diverse the models, the better the council output. Using the same model for all three defeats the purpose.

**Example configuration:**
```json
{
  "council_models": [
    "ollama/kimi-k2.6:cloud",
    "ollama/deepseek-v4-pro:cloud",
    "ollama/gemma4:31b-cloud"
  ],
  "default_timeout": 900,
  "max_tokens": 8192
}
```

## Perspectives

Each model gets a different analytical lens:

| Perspective | Role | Focus |
|------------|------|-------|
| **Strategos** | Strategic analyst | Big-picture strategy, business impact, feasibility, ROI |
| **Analyticos** | Data & logic analyst | Technical correctness, edge cases, data quality, consistency |
| **Creativos** | Creative thinker | Novel alternatives, user experience, unconventional approaches |

## How to Run a Council

### Step 1: Prepare the Context

Gather all relevant data BEFORE spawning. Council agents cannot browse the web or access your conversation history. Paste everything they need inline.

### Step 2: Spawn 3 Parallel Subagents

Read the model names from `council-config.json` and spawn each with a different perspective:

```
sessions_spawn(
  runtime: "subagent",
  mode: "run",
  model: <first model from config>,
  label: "Council-Strategos",
  lightContext: true,
  runTimeoutSeconds: <default_timeout fro

README.md

# Council of LLMs

Multi-model council deliberation for OpenClaw. Spawn 3 parallel subagents with different models and perspectives, then synthesize their outputs into a unified verdict.

## Why This Exists

Single-model "councils" — where one subagent roleplays 3 experts — fail repeatedly. They produce context overflow (300-600k tokens), shallow analysis, and empty outputs. Real deliberation requires genuinely different models providing independent perspectives.

## How It Works

1. **Spawn 3 parallel subagents**, each with a different model:
   - **Strategos** (kimi-k2.6) — strategy, business impact, feasibility
   - **Analyticos** (deepseek-v4-pro) — data quality, technical correctness, edge cases
   - **Creativos** (gemma4:31b) — creative alternatives, UX, novel approaches

2. **Each agent analyzes independently** with their specific lens

3. **Synthesize** — merge verdicts into consensus, disagreements, blind spots, and action items

## Quick Start

```python
# Spawn all 3 in parallel
sessions_spawn(model="kimi-k2.6:cloud", label="Council-Strategos", ...)
sessions_spawn(model="deepseek-v4-pro:cloud", label="Council-Analyticos", ...)
sessions_spawn(model="gemma4:31b-cloud", label="Council-Creativos", ...)

# Wait for all 3 to complete, then synthesize
```

## Critical Rules

- **Paste ALL context inline** — agents have no conversation history
- **Keep task descriptions under 2000 words** — longer = context overflow = failure
- **Use `lightContext: true`** — always
- **Set `runTimeoutSeconds: 900`** — councils need time
- **Wait for ALL 3 to complete** — don't synthesize early

## Configuration

Models are read from `~/.openclaw/council-config.json`:

```json
{
  "council_models": [
    "ollama/kimi-k2.6:cloud",
    "ollama/deepseek-v4-pro:cloud",
    "ollama/gemma4:31b-cloud"
  ],
  "default_timeout": 900,
  "max_tokens": 8192
}
```

## Companion Skill

- **[Subagent Orchestration](https://github.com/wahajahmed010/subagent-orchestration)** — Core delegation patterns, sandbox constraints, timeout strategy, and failure mode reference. Council of LLMs builds on these patterns for multi-agent deliberation.

## Install

```bash
# Install both skills together
clawhub install council-of-llms
clawhub install subagent-orchestration

# Or from GitHub
openclaw skills install wahajahmed010/council-of-llms
openclaw skills install wahajahmed010/subagent-orchestration
```

## ClawHub

Published at: https://clawhub.com/skills/council-of-llms

## License

MIT-0

_meta.json

{
  "ownerId": "kn7104e9v8eyfbk1y69y0yr7th850741",
  "slug": "council-of-llms",
  "version": "2.0.0",
  "publishedAt": 1778761890186
}

skill-card.md

## Description:

Real multi-model council deliberation for OpenClaw subagents that spawns three parallel subagents with distinct analytical perspectives and synthesizes their independent outputs into a unified verdict.

This skill is ready for commercial/non-commercial use.

## Publisher:

[wahajahmed010](https://clawhub.ai/user/wahajahmed010)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and engineers use this skill to run multi-model reviews, debates, stress tests, and decision analyses by assigning strategic, analytical, and creative perspectives to separate subagents before synthesizing a final verdict.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Configured council models may be cloud-backed, so copied context can be sent to external model providers.

Mitigation: Review configured models before use and avoid pasting secrets, credentials, customer data, regulated information, or proprietary material unless sharing with those providers is acceptable.

Risk: The skill can create a local council-review markdown file in the workspace.

Mitigation: Review generated files before sharing, committing, or using them as decision records.

Risk: The skill depends on companion subagent orchestration behavior.

Mitigation: Review or pin the companion subagent skill before installing or running the council workflow.

## Reference(s):

- [Council Of Llms on ClawHub](https://clawhub.ai/wahajahmed010/skills/council-of-llms)
- [Subagent Orchestration companion skill](https://github.com/wahajahmed010/subagent-orchestration)

## Skill Output:

**Output Type(s):** [text, markdown, guidance, configuration]

**Output Format:** [Markdown synthesis with structured verdicts, consensus points, disagreements, blind spots, and action items]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May create a local council-review markdown file in the workspace.]

## Skill Version(s):

2.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.