council-2
Council Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation.
Best use case
council-2 is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Council Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation.
Teams using council-2 should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/council-2/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How council-2 Compares
| Feature / Agent | council-2 | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Council Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Council - Chamber Orchestration Pattern
Instead of spawning separate agent silos, create a **Council Chamber** where multiple expert personas deliberate in a single session with cross-pollination and unified transcript.
## Prerequisites
- SQLite3 (member database)
- Graphiti service (Memory Bridge)
- Clawdbot gateway (sessions_spawn)
## Setup
Initialize council database:
```bash
bash command:"{baseDir}/init-db.sh"
```
## 🏛️ The Chamber Pattern
**Traditional Approach** (Silos):
- Spawn 3 separate agents
- Each analyzes independently
- No cross-pollination
- Fragmented output
**Chamber Approach** (Meeting Room):
- Single agent session
- Moderates multiple personas
- Structured turn-taking
- Unified deliberation transcript
## Tools
### council_chamber
Start a Council Chamber session (recommended).
**Usage:**
```bash
bash command:"
TOPIC='YOUR_TOPIC'
MEMBERS='architect,analyst,security'
{baseDir}/references/chamber-orchestrator.sh \"\$TOPIC\" \"\$MEMBERS\"
"
```
**What it does**:
1. Fetches Graphiti context (Memory Bridge)
2. Loads member personas from database
3. Constructs chamber task with turn structure
4. Creates session record
5. Outputs task for sessions_spawn
### council_list_members
List all registered members.
**Usage:**
```bash
bash command:"sqlite3 -header -column ~/.clawdbot/council.db 'SELECT id, name, role FROM council_members'"
```
### council_add_member
Register new member.
**Usage:**
```bash
bash command:"
sqlite3 ~/.clawdbot/council.db \"
INSERT INTO council_members (id, name, role, system_message, expertise)
VALUES ('MEMBER_ID', 'NAME', 'ROLE', 'SYSTEM_MESSAGE', 'EXPERTISE');
\""
```
## Chamber Session Structure
**3-Turn Deliberation**:
1. **Turn 1: Initial Analysis**
- Each persona provides their perspective
- Distinct voices maintained
2. **Turn 2: Cross-Pollination**
- Members critique each other's points
- Real-time responses
- Healthy debate
3. **Turn 3: Synthesis**
- Find common ground
- Resolve disagreements
- Executive Summary for user
## Default Members
| ID | Name | Role |
|----|------|------|
| architect | System Architect | Technical Design |
| analyst | Technical Analyst | Research & Analysis |
| security | Security Officer | Risk Assessment |
| designer | UX Designer | User Experience |
| strategist | Business Strategist | ROI & Strategy |
## Example
```bash
# User: "Start council on Salesforce integration"
council_chamber topic:"Salesforce Integration" members:"architect,strategist"
# Output:
# 🏛️ Convening Council Chamber...
# 🧠 Memory Bridge: [Retrieved 10 facts about Salesforce]
# 👥 Loaded 2 personas
# ✅ Chamber Task ready for sessions_spawn
```
**Benefits**:
- ✅ Cross-pollination (members respond to each other)
- ✅ Single transcript (one .jsonl file)
- ✅ Shared context (Memory Bridge loaded once)
- ✅ Structured output (3-turn deliberation)Related Skills
llm-council
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
council
Send an idea to the Council of the Wise for multi-perspective feedback. Spawns sub-agents to analyze from multiple expert perspectives. Auto-discovers agent personas from agents/ folder.
portfolio-watcher
Monitor stock/crypto holdings, get price alerts, track portfolio performance
portainer
Control Docker containers and stacks via Portainer API. List containers, start/stop/restart, view logs, and redeploy stacks from git.
portable-tools
Build cross-device tools without hardcoding paths or account names
polymarket
Trade prediction markets on Polymarket. Analyze odds, place bets, track positions, automate alerts, and maximize returns from event outcomes. Covers sports, politics, entertainment, and more.
polymarket-traiding-bot
No description provided.
polymarket-analysis
Analyze Polymarket prediction markets for trading edges. Pair Cost arbitrage, whale tracking, sentiment analysis, momentum signals, user profile tracking. No execution.
polymarket-agent
Autonomous prediction market agent - analyzes markets, researches news, and identifies trading opportunities
polymarket-5
Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data.
polymarket-4
Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data.
polymarket-3
Query Polymarket prediction market odds and events via CLI. Search for markets, get current prices, list events by category. Supports sports betting (NFL, NBA, soccer/EPL, Champions League), politics, crypto, elections, geopolitics. Real money markets = more accurate than polls. No API key required. Use when asked about odds, probabilities, predictions, or "what are the chances of X".