Claude Code Skill v2.10.4 MIT License

AI Consultants

Query 15 AI models simultaneously. Get diverse perspectives, weighted synthesis, and multi-agent debate for your coding decisions.

View on GitHub npm
Supported agents: Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf, Aider, Amp, Kimi, Standalone Bash

A council of AI experts for every coding decision

AI Consultants is a multi-model deliberation system. Instead of relying on a single AI for coding advice, it queries up to 15 different AI models in parallel — each with a unique persona and focus area.

Every consultant provides a confidence-scored response. The system then synthesizes all perspectives into a weighted recommendation, highlights points of agreement and disagreement, and optionally runs multi-round debates where consultants critique each other's positions.

The result: better decisions through cognitive diversity. When 12 out of 15 models agree, you can move fast. When they disagree, you know exactly where the risks are.

Everything you need

Built for developers who want more than a single opinion.

01

15 AI Consultants

Gemini, Codex, Mistral, Kilo, Cursor, Aider, Amp, Kimi, Claude, Qwen3, GLM, Grok, DeepSeek, MiniMax, and Ollama. Each with a unique persona.

02

Automatic Synthesis

All responses are combined into a single weighted recommendation with confidence scoring and consensus analysis.

03

Multi-Agent Debate

Consultants critique each other across multiple rounds. Positions evolve. Anonymous peer review identifies the strongest arguments.

04

Smart Routing

Questions are classified by category and routed to the most relevant consultants. Security questions go to security experts first.

05

Quality Tiers

Premium, standard, and economy model tiers. Choose max_quality for critical decisions or fast for quick checks.

06

Cost Control

Budget enforcement, semantic caching, cost-aware routing, and response limits. Stay within budget without sacrificing quality.

From question to recommendation

Query Classify Parallel Queries Vote Synthesize Report
01

Classify

Your question is analyzed and categorized — architecture, security, performance, code review, quick syntax — to determine which consultants are most relevant and what depth of analysis is needed.

02

Consult

Selected consultants are queried in parallel. Each responds with a structured JSON output including a summary, detailed analysis, pros/cons, and a confidence score from 1 to 10.

03

Synthesize

All responses are aggregated. Consensus is calculated, confidence intervals computed, and a weighted recommendation is generated using your chosen synthesis strategy.

04

Debate

Optionally, consultants enter a multi-round debate. They critique each other's positions, update their confidence scores, and converge (or diverge) on a recommendation. Panic mode triggers extra rigor when uncertainty is high.

15 consultants, 15 perspectives

Each consultant has a distinct persona that shapes their analysis. The invoking agent is automatically excluded to prevent self-consultation.

CLI-Based — 9 consultants
Google Gemini
The Architect
Design, scalability, enterprise
OpenAI Codex
The Pragmatist
Simplicity, proven solutions
Mistral Vibe
The Devil's Advocate
Edge cases, risks, security
Kilo Code
The Innovator
Creative, unconventional
Cursor
The Integrator
Full-stack perspective
Aider
The Pair Programmer
Collaborative coding
Amp
The Systems Thinker
System design, interactions
Kimi
The Eastern Sage
Holistic, balanced views
Claude
The Synthesizer
Big picture, synthesis
API-Based — 5 consultants
Qwen3
The Analyst
Data-driven, metrics
GLM
The Methodologist
Structured approaches
Grok
The Provocateur
Challenge conventions
DeepSeek
The Code Specialist
Algorithms, code gen
MiniMax
The Pragmatic Optimizer
Performance, efficiency
Local — 1 consultant
Ollama
The Local Expert
Privacy-first, zero API cost

Up and running in 30 seconds

Option A: npx (recommended)

# Run directly — no install needed
npx ai-consultants "How should I structure my auth system?"

# With a preset
npx ai-consultants --preset balanced "Redis or Memcached?"

# Run diagnostics
npx ai-consultants doctor --fix

# Install slash commands for Claude Code
npx ai-consultants install

Option B: Claude Code skill (curl | bash)

# Install the skill
curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/scripts/install.sh | bash

# Ask your first question
/ai-consultants:consult "How should I structure my auth system?"

Option C: Standalone bash

# Clone and set up
git clone https://github.com/matteoscurati/ai-consultants.git
cd ai-consultants
./scripts/doctor.sh --fix

# Run a consultation
./scripts/consult_all.sh "How should I structure my auth system?"
Works with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf (via SkillPort), Aider (via AGENTS.md), Amp, Kimi, and standalone bash.

Presets and strategies

Presets
Preset Consultants Use Case
max_qualityAll + debate + reflectionCritical decisions
medium4 + light debateGeneral questions
fast2Quick checks
balanced4 (Gemini, Codex, Mistral, Kilo)Standard consultations
high-stakesAll + debateCritical decisions
localOllama onlyFull privacy
securitySecurity-focused + debateSecurity reviews
Synthesis Strategies
Strategy Description
majorityMost common answer wins (default)
risk_averseWeight conservative responses higher
security_firstPrioritize security considerations
cost_cappedPrefer simpler, cheaper solutions
compare_onlyNo recommendation, just comparison
Key Environment Variables
# Core features
ENABLE_DEBATE=true           # Multi-agent debate
ENABLE_SYNTHESIS=true        # Automatic synthesis
ENABLE_SMART_ROUTING=true    # Intelligent consultant selection
ENABLE_PANIC_MODE=auto       # Automatic rigor for uncertainty

# Defaults
DEFAULT_PRESET=balanced
DEFAULT_STRATEGY=majority

# Ollama (local models)
ENABLE_OLLAMA=true
OLLAMA_MODEL=qwen2.5-coder:32b

# Cost management
MAX_SESSION_COST=1.00        # Budget limit in USD
WARN_AT_COST=0.50
Copied to clipboard