No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by albertofettucini · Agent Tool · ★ 107
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Council safe to install? View the security audit →
Council One question. A roundtable of AI minds. You decide. A native macOS app that puts the same question to several LLMs, lets them critique each other blind, and shows you where they agree — and where they don't. The idea Asking one model a hard question gives you one model's blind spots. Council convenes a panel instead. The same prompt goes to several advisors at once — Claude, GPT, Gemini and more — each answers independently, and then the interesting part begins. How it works Ask. Pose a question to your council (three advisors; each seat can be any of twelve backends). Parallel answers. Every advisor responds at once, streaming live in its own panel. Blind peer review. Each advisor critiques the others' answers without knowing who wrote them — no brand bias, just the argument. Divergence — with a score. A 0–100 read of how far apart the council landed, how many camps formed, and who the outlier is. It measures agreement, not correctness. Debate
| Stars | 107 |
| Forks | 6 |
| Language | Swift |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 65.6967350377193/100 |
| Last Updated | 2026-07-25 |
| Created | 2026-06-06 |
| Platforms | claude-code, gemini |
| Est. Tokens | ~16k |
These tools work well together with Council for enhanced workflows:
Looking for a Council alternative? If you're comparing Council with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A native macOS menu bar app that shows your Claude.ai usage at a glance — colour-coded icon, live counter, res
Copy AI conversations as clean Markdown Context Bundles — one click from ChatGPT, Claude, Gemini, DeepSeek, Gr
c4 GenAI Suite
Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP to
Native macOS app to monitor Claude AI usage limits and watch your coding sessions live
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and ar
Explore other popular agent tool tools:
Council is Ask several AI models one question — they answer in parallel, critique each other blind, and you decide. Native macOS, bring-your-own-keys.. It is categorized as a Agent Tool with 107 GitHub stars.
Council is primarily written in Swift. It covers topics such as ai, ai-tools, anthropic.
You can find installation instructions and usage details in the Council GitHub repository at github.com/albertofettucini/Council. The project has 107 stars and 6 forks, indicating an active community.
Council is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Council on Agent Skills Hub include Claude-Usage-Monitor, ctxport, c4-genai-suite. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: