A tool that asks several AI systems to review code, validate plans, or assess architecture, then combines their opinions into a consensus-oriented result.

Use it for multi-model code reviews, checking implementation plans, and comparing architectural recommendations.

It reduces reliance on one automated opinion when reviewing changes or making important technical decisions.

council — Plugin for Claude Code by rube-de/cc-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/rube-de/cc-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/rube-de/cc-skills/council/github.svg)](https://agentmods.dev/plugins/rube-de/cc-skills/council)

Your own site

<a href="https://agentmods.dev/plugins/rube-de/cc-skills/council"><img src="https://agentmods.dev/badge/plugins/rube-de/cc-skills/council/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/rube-de/cc-skills/council"><img src="https://agentmods.dev/badge/plugins/rube-de/cc-skills/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 3 skills, 1 command, 7 agents cost 2,179 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

council scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json#council · 21 lines

What it actually says

{
  "name": "council",
  "description": "AI Council - Orchestrate multiple AI consultants (Gemini 3.8 Flash, Codex, GLM-5.3, Kimi K3) for consensus-driven code reviews, plan validation, and architectural decisions",
  "version": "2.21.1",
  "source": "./plugins/council",
  "category": "code-review",
  "author": {
    "name": "rube-de",
    "url": "https://github.com/rube-de"
  },
  "keywords": [
    "ai-council",
    "code-review",
    "multi-model",
    "consensus",
    "gemini",
    "codex",
    "glm",
    "kimi"
  ]
}

Contents

What it installs

The manifest is a name and a version. 3 skills, 1 command, 7 agents travel with it, and installing the plugin installs all of them — 2,179 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#council in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 7.9 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed 8fbc02da9097
6d ago Changed 0d53334828fd
9d ago Changed 8ed9980933be
10d ago Changed 66fe8ee6288d
11d ago Changed de0e18b23e4f
13d ago Changed 74f152307bf3
23d ago Changed 6916fc3ca45d
1mo ago Changed 37cec5ba9163
1mo ago First seen · 21 lines scan A b6022daae4d4

Subscribe to this mod's changes

council is a plugin published in the GitHub repository rube-de/cc-skills (10 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Claude Code Code review Multi-Agent agent-teams ai-council claude-code-plugin

review-all

Comprehensive, project-agnostic, multi-agent code review for Claude Code with verification to eliminate false positives.

ncoevoet/claude-review-all · not measured

great-cto

You already have the agent. This is everything around it. greatcto runs Claude Code as a pipeline of 72 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.

avelikiy/great_cto · not measured

cursor

Local Cursor Agent CLI delegation: multi family consults, Composer implementation in owned worktrees, review, resumable history, background jobs, and setup health checks.

okisdev/claude-code-fusion · not measured

asdlc

PRD Implementor, PR Review, PDQC, Jira leg — commands and subagents.

mumerfarooq-con/asdlc-tools · not measured

agent-harness

Multi-agent harness for Claude Code: Planner→Generator→Evaluator sprints executed as background dynamic workflows (Agent-tool fallback), fable/opus/sonnet/haiku model routing with per-role reasoning effort, harness-engineering framework for design/diagnosis, and Anthropic 2026-04-04 P-G-E pattern.

bouob/agent-harness · not measured

humanizer

Rewrite AI-sounding text so it reads like the writer without changing what it says.

blader/humanizer · not measured