What makes conclave notable?

959 downloads. Trust evidence available

How should conclave 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

conclave

Conclave is a multi-agent reasoning skill that orchestrates multiple AI CLIs into structured debates. Each agent independently analyzes the problem, challenges competing arguments, identifies flaws and contradictions, and refines the reasoning through multiple rounds of discussion — helping you reach more reliable conclusions than relying on a single AI. Skill: conclave Owner: mclyang Summary: Conclave is a multi-agent reasoning skill that orchestrates multiple AI CLIs into structured debates. Each agent independently analyzes the problem, challenges competing arguments, identifies flaws and contradictions, and refines the reasoning through multiple rounds of discussion — helping you reach more reliable conclusions than relying on a single AI. Tags: latest:1.6.7 Vers

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

959

Updated

Oct 12, 2026

Version

1.6.7

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 959 downloads reported by the source. Last updated 10/12/2026.

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 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 959 downloadsadoption · observed Oct 12, 2026
Latest release: 1.6.7release · observed Aug 16, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.6.7release
Field lessons 23-24: never edit a prior debate's files (follow-up=new arena, merges=new file); wait for all panelists (late != absent) before convergence/final step
Observed Aug 16, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s177gyq4npjm4wcj5rqjb4cegh8cdfps:conclave-skill

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-mclyang-conclave-skill/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

157,738 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: conclave
description: "Conclave is a multi-agent reasoning skill that orchestrates multiple AI CLIs into structured debates. Each agent independently analyzes the problem, challenges competing arguments, identifies flaws and contradictions, and refines the reasoning through multiple rounds of discussion — helping you reach more reliable conclusions than relying on a single AI."
version: 1.6.7
author: Hermes Agent
metadata:
hermes:
tags: [Debate, Multi-Agent, Decision, Claude, Codex, Gemini, Qwen, DeepSeek, Doubao, Ark, Manus, Install, Update, Export, Archive]
---

# Conclave — Multi-Agent Structured Debate & Adjudication

Given a user topic, convene AI agents to independently posit arguments, engage in anonymous cross-examination, converge, and sign off unanimously, producing a chair-adjudicated final markdown report.

Use for high-stakes decisions (pricing structure, contract risk, architecture selection, investment judgment). Do not use for daily trivia.

## ⚠️ Full Capability Disclosure (read before installing)

This skill does **significantly more** than "debate orchestration". By design it:

- **Installs and updates global CLI tools** (`npm install -g`, brew, apt, etc.) via `scripts/install.sh` and pre-flight self-updates.
- **Inspects local auth state** (checks for API keys, OAuth tokens, keychain status) without reading secret values.
- **Transmits your debate topic** to 6 third-party AI cloud APIs (Claude/OpenAI, Google, Alibaba, ByteDance/Ark, Manus).
- **Persists full debate records** indefinitely under `~/.hermes/debates/` (briefs, raw agent outputs, verdicts, votes).
- **Mandatorily exports** the entire arena to the current working directory after every debate.
- **Calls external REST APIs** (Manus `api.manus.im`) with the debate final draft.

**Do not install if** you are not comfortable with global package changes, third-party AI services seeing your content, or full debate archives being retained and copied into your working directory.

## ⚠️ Security & Privacy Notice

**Before using Conclave, read this.**

1. **Local data persistence**: Every debate creates a persistent folder under `~/.hermes/debates/` containing the full brief, all agent outputs, anonymity mappings, chair verdicts, and final reports. These files remain on disk indefinitely unless you manually delete them. Do not use Conclave for topics containing regulated personal data, trade secrets, or classified information unless you accept this retention risk.

2. **External data sharing**: Panelists (Claude, Codex, Gemini, Qwen, DeepSeek, Doubao) receive debate prompts via their respective cloud APIs. The external advisor (Manus) receives the final draft and round summaries via MCP or direct REST polling. By running a debate, you are transmitting your topic and context to these third-party AI providers. Review each provider's data policy before debating sensitive topics.

3. **Credential handling**: This skill **never** prompts for, stores, or logs passwor

README.md

# Conclave

[![Hermes Skill](https://img.shields.io/badge/Hermes-Skill-blue)](https://github.com/MCLYang/conclave-skill)
[![Version](https://img.shields.io/badge/version-1.6.2-green)]()

> **Conclave** is a multi-agent reasoning skill that orchestrates multiple AI CLIs into structured debates. Each agent independently analyzes the problem, challenges competing arguments, identifies flaws and contradictions, and refines the reasoning through multiple rounds of discussion — helping you reach more reliable conclusions than relying on a single AI.

---

## Core Capabilities

| Capability | Description |
|------------|-------------|
| **Independent Positioning** | Five agents (Hermes, Claude, Codex, Gemini, Qwen) analyze the same brief in parallel, unseen by each other, preventing anchoring. |
| **Anonymous Rebuttal** | Each agent receives the other four's R1 arguments (anonymized) and must identify at least one fatal flaw plus a concrete alternative solution. |
| **Structured Convergence** | Chair (Hermes) synthesizes consensus and divergence points after each round; divergence points are sent back for further debate (dynamic rounds, hard ceiling 8). |
| **Unanimous Sign-off** | Final draft circulated to all five; any objection must include a specific clause, specific reason, and an executable alternative. No-destruction-without-construction = invalid vote. |
| **External Audit** | Manus reviews the final draft before delivery; a fatal-level objection triggers an extra round. |
| **Automatic Archiving** | Every debate gets its own folder; all intermediate files are persisted by round. See **Security & Privacy** below for retention controls. |

## ⚠️ Security & Privacy

- **Data persists locally**: Debates are stored under `~/.hermes/debates/` indefinitely. Do not debate topics containing regulated personal data, trade secrets, or classified information unless you accept this risk.
- **Data leaves your machine**: Prompts are sent to Claude (Anthropic), Codex (OpenAI), Gemini (Google), and Qwen (Alibaba) cloud APIs. The optional Manus advisor receives the final draft via MCP. Review each provider's data policy.
- **No password storage**: This skill never prompts for, stores, or logs passwords. The macOS keychain must be unlocked manually by the user in an interactive terminal before background sessions.
- **Input validation**: Topic slugs are sanitized to 1-32 lowercase letters, digits, and hyphens.
- **Cleanup**: Run `bash ~/.hermes/skills/conclave/scripts/cleanup.sh [days]` to purge debates older than the retention period. Default is 90 days; use `0` for a dry-run preview.

---

## Quick Start

```bash
# 0. First time on this machine? Detect + install all CLIs/dependencies,
#    then configure each provider key it flags as [ACTION]
bash ~/.hermes/skills/conclave/scripts/install.sh

# 1. Initialize a debate arena
bash ~/.hermes/skills/conclave/scripts/init_debate.sh <topic-slug>

# 2. Pre-flight check (update all CLIs, then ignition-ping every agent)

_meta.json

{
  "ownerId": "kn7fgzd63hpn9jfpqcfc6tj3tn8cdng2",
  "slug": "conclave-skill",
  "version": "1.6.7",
  "publishedAt": 1786844192300
}

references/consensus-protocol-v1.md

# Conclave Consensus Protocol v1.1

Chair-audited revision of the v0.1 architecture proposal, amended by external review (2026-08-14). Highest objective: **maximize decision quality per unit cost — never consensus, never model count, never debate length.**

Two orthogonal tag systems are used throughout:
- Implementation status: **[CORE]** current workflow · **[V1]** live now · **[L2]** deferred (needs data/infra)
- Rigor level: **[FORMAL]** standard statistical theory · **[ESTIMATOR]** needs data · **[HEURISTIC]** engineering proxy · **[POLICY]** human-set rule · **[EXPERIMENTAL]** unvalidated

Every soft number in any Conclave output must carry a rigor tag. Fake precision is the enemy.

---

## 0. What was rejected from v0.1 and why

| v0.1 item | Verdict | Reason |
|---|---|---|
| §13 w̃ᵢ = wᵢ/(1+λΣρᵢⱼwⱼ) | **REJECTED** | Ad hoc. The statistically principled aggregation of correlated estimators is inverse-covariance (GLS) weighting: w* ∝ Σ⁻¹1. Anything else needs empirical justification we don't have. |
| §17 Priority = I × D × U (product) | **REJECTED** | Product of three [0,1] terms collapses all priorities into noise. Replaced by decision-relevance-first ranking (§5 below). |
| §20 literal EVSI | **REPLACED** | True EVSI needs a likelihood model over what a new agent would say — intractable. Replaced by computable proxy: Decision-Flip Value (§6). |
| §3 fixed 7-model council | **BLOCKED** | Only 4 panelist CLIs exist (Claude, Codex, Gemini, Qwen) + Hermes + Manus. Seed/DeepSeek/Grok are not available. See §2. |
| §29C full calibration DB | **SCOPED** | Most strategic decisions never receive ground truth; Brier scores are uncomputable for them. Calibration tracking is restricted to *verifiable predictions* only (§9). |
| Multiplicative weight wᵢ = hᵢ·rᵢ·qᵢ | **[HEURISTIC]** kept with defaults | No calibration data yet. Default hᵢ = 1 for all; rᵢ, qᵢ set by chair per debate, logged, never presented as precise. |

## 1. Objective

a* = argmin_a E[L(a,θ) | E] + λ·Cost(process)

Consensus is an intermediate statistic, never the target. The chair optimizes the decision under a loss function the USER must supply or approve (default for investments: expected percentage drawdown of the account).

## 2. Modes (resource-constrained reality)

| Mode | Panelists | When | Manus |
|---|---|---|---|
| Quick | 2 CLIs + Hermes | low-risk, fast | off by default |
| Standard | 4 CLIs + Hermes | default (current implementation) | trigger-based (§7) |
| Deep | **BLOCKED** until additional panelist CLIs (DeepSeek/Grok/etc.) are installed and pass preflight | high-stakes | preferred |

Mode selection is declared by the chair in the brief; the user may override.

## 3. Round structure [CORE + V1]

- **R1 independence is absolute [CORE]**: no panelist sees another's output. Prompts identical except the explicit role-letter assignment (field lesson 13).
- **Structured R1 output [V1]**: each panelist must return JSON-ish blocks: position, claims[], evidence[], assumpt

references/panelists.md

# Panelist Roster

Six AI panelists + one external advisor. All CLI calls require `no_proxy='*'` prepended.

## 1. Hermes (Chair & Panelist)

- This agent itself. Positioning and rebuttals are drafted in-session by the chair, written to disk in the same format as the other four.
- Red line: must not favor itself; views struck down are still recorded under "rejected positions".

## 2. Claude Code

- Command: `no_proxy='*' claude -p '<prompt>' --max-turns 1`
- Auth: official OAuth ([email protected]), credentials stored in macOS login keychain.
  Background sessions may fail to read the keychain (security exit 36).
  **DO NOT put passwords in prompts or scripts.** The user must manually unlock the keychain in an interactive terminal before starting a background debate session (macOS only; N/A on Linux/Windows where only `~/.claude/.credentials.json` is checked):
  ```
  security unlock-keychain ~/Library/Keychains/login.keychain-db
  ```
  If still 401: check for and move aside old `~/.claude/.credentials.json`, then retry.
- Update: `claude update`
- Install: `npm install -g @anthropic-ai/claude-code` (or run `scripts/install.sh` to install everything at once)
- Ping: `no_proxy='*' claude -p 'reply with one word: pong' --max-turns 1`

## 3. Codex

- Command: `no_proxy='*' codex exec --skip-git-repo-check -c model_reasoning_effort="medium" '<prompt>'`
  For important sessions, replace medium with xhigh.
- Auth: cmdme.cn relay, sk- key in `~/.codex/auth.json`; in config.toml set
  `requires_openai_auth = false`, `wire_api = "responses"`, `base_url = "https://cmdme.cn"`.
- Pitfall: exec defaults to a read-only sandbox; file writes are rejected → prompts must require "full text to stdout",
  and the chair extracts the output via `process(action='log', offset=0, limit=400)` to disk.
- Update: `codex update` (or `npm install -g @openai/codex@latest` when npm-managed)
- Install: `npm install -g @openai/codex`
- Ping: `no_proxy='*' codex exec --skip-git-repo-check 'reply with one word: pong'`

## 4. Gemini CLI

- Command: `no_proxy='*' GEMINI_CLI_TRUST_WORKSPACE=true zsh -i -c 'gemini -p "<prompt>"'`
  (On Linux/Windows without zsh, preflight.sh auto-falls back to `bash -i -c` — both source rc files for env keys.)
- Pitfall: since 0.55.1 a trust-directory check was added; non-interactive calls must carry `GEMINI_CLI_TRUST_WORKSPACE=true`, otherwise the CLI refuses to run.
- Auth / env: `GOOGLE_GEMINI_BASE_URL` + `GEMINI_API_KEY` (persisted in user shell rc).
  Key format determines provider: `AQ.Ab8…` = Google official (base generativelanguage.googleapis.com),
  `sk-…` = cmdme relay. Mixing them causes 401.
  Note: non-interactive shells may not read rc files — call via `zsh -i -c` or explicitly export variables.
- Update: `npm install -g @google/gemini-cli@latest`
- Install: `npm install -g @google/gemini-cli`
- Ping: `no_proxy='*' GEMINI_CLI_TRUST_WORKSPACE=true zsh -i -c 'gemini -p "reply with one word: pong"'`

## 5. Qwen

- Command: `no_proxy='*'

Github ReposUpdated 3d 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.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular