hive-mind-advanced

hive-mind-advanced is a skill for Claude Code from ruvnet/ruflo. It costs 25 tokens per session (3,918 once invoked), scanned A, original, MIT.

An advanced system for coordinating groups of specialized agents through a strategic leader, shared memory, and consensus rules. Different agents can handle research, coding, testing, design, review, or documentation.

In plain words
What is it for?
Use it to organize multi-agent projects, assign specialized roles, coordinate decisions, share memory, and adapt how agents work together.
Why use it?
It provides a structure for splitting complex work among agents while keeping their decisions and knowledge connected. This helps when one agent cannot reasonably handle every role.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

Part of the claude-flow plugin — 134 skills, 52 commands, 11 agents, 4 hooks shipped together

not rated 71krepo +669 2d ago A scan Socket: warnSnyk: warnSkillSpector: warn 25 tokens original MIT

Good fit Use it to organize multi-agent projects, assign specialized roles, coordinate decisions, share memory, and adapt how agents work together.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruvnet/ruflo/hive-mind-advanced
About the project

Ruflo is an execution and coordination layer for Claude Code and Codex that equips AI coding agents with tools, memory, control loops, sandboxes, and collaboration mechanisms. Developers use it to organize specialized agents into swarms, coordinate workflows, retain knowledge across sessions, and communicate across machines. The catalogue entries are Ruflo’s skills, commands, agents, hooks, and plugin components.

ruvnet/ruflo · 71,074 stars · on GitHub · cognitum.one

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.

Any agent
npx skills add ruvnet/ruflo --skill hive-mind-advanced
Clone the repo
git clone --depth 1 https://github.com/ruvnet/ruflo

Made for: Claude Code.

Or install claude-flow, the plugin that ships this one along with the rest of its 134 skills, 52 commands, 11 agents, 4 hooks.

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.

agentmods badge for hive-mind-advanced

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruflo/hive-mind-advanced.svg)](https://agentmods.dev/skills/ruvnet/ruflo/hive-mind-advanced)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruflo/hive-mind-advanced"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/hive-mind-advanced.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket warn 18 Mar 2026
  • Snyk warn 1 Mar 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 39 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 61
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 64
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 67
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 74
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 77
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 80
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 83
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 86
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 93
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 96
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 99
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 110
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 113
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 116
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 119
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 229
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 244
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 258
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 261
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 375
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.03918
Opus 5 $0.00013 $0.01959
Sonnet 5 $0.00005 $0.00784
Haiku 4.5 $0.00003 $0.00392

Measured 4d ago against content hash afdb57e9452e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hive-mind-advanced 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 4d ago.

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.

Origin

Copies of this mod

6 near-identical copies found in the catalogue:

.agents/skills/hive-mind-advanced/SKILL.md · 713 lines

How it starts

The opening of the file, as written. The whole thing — 713 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hive Mind Advanced Skill

Master the advanced Hive Mind collective intelligence system for sophisticated multi-agent coordination using queen-led architecture, Byzantine consensus, and collective memory.

Overview

The Hive Mind system represents the pinnacle of multi-agent coordination in Claude Flow, implementing a queen-led hierarchical architecture where a strategic queen coordinator directs specialized worker agents through collective decision-making and shared memory.

Core Concepts

Architecture Patterns

Queen-Led Coordination

  • Strategic queen agents orchestrate high-level objectives
  • Tactical queens manage mid-level execution
  • Adaptive queens dynamically adjust strategies based on performance

Worker Specialization

  • Researcher agents: Analysis and investigation
  • Coder agents: Implementation and development
  • Analyst agents: Data processing and metrics
  • Tester agents: Quality assurance and validation
  • Architect agents: System design and planning
  • Reviewer agents: Code review and improvement
  • Optimizer agents: Performance enhancement
  • Documenter agents: Documentation generation

Collective Memory System

  • Shared knowledge base across all agents
  • LRU cache with memory pressure handling
  • SQLite persistence with WAL mode
  • Memory consolidation and association
  • Access pattern tracking and optimization

Consensus Mechanisms

Majority Consensus Simple voting where the option with most votes wins.

Weighted Consensus Queen vote counts as 3x weight, providing strategic guidance.

Byzantine Fault Tolerance Requires 2/3 majority for decision approval, ensuring robust consensus even with faulty agents.

Getting Started

1. Initialize Hive Mind

# Basic initialization
npx claude-flow hive-mind init

# Force reinitialize
npx claude-flow hive-mind init --force

# Custom configuration
npx claude-flow hive-mind init --config hive-config.json

2. Spawn a Swarm

# Basic spawn with objective
npx claude-flow hive-mind spawn "Build microservices architecture"

# Strategic queen type
npx claude-flow hive-mind spawn "Research AI patterns" --queen-type strategic

# Tactical queen with max workers
npx claude-flow hive-mind spawn "Implement API" --queen-type tactical --max-workers 12

# Adaptive queen with consensus
npx claude-flow hive-mind spawn "Optimize system" --queen-type adaptive --consensus byzantine

# Generate Claude Code commands
npx claude-flow hive-mind spawn "Build full-stack app" --claude

Read the full file on GitHub · 713 lines

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.

  1. 4d ago First seen · 713 lines · 25 tokens per session scan A afdb57e9452e

Subscribe to this mod's changes

hive-mind-advanced is a skill published in the GitHub repository ruvnet/ruflo (71,074 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 3,918 once invoked, about $0.0001 per session on Opus 5. 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.