hive-mind

hive-mind is a skill for Claude Code, Codex from proffesor-for-testing/agentic-qe. It costs 61 tokens per session (433 once invoked), scanned A, a copy of hive-mind, MIT.

A system for coordinating multiple AI agents that can use different team structures and agreement methods. Byzantine fault tolerance is a way to keep working when some participants provide incorrect or conflicting information.

In plain words
What is it for?
Use it for distributed coordination, fault-tolerant operations, multi-agent consensus, and collective decision-making across complex tasks.
Why use it?
It helps agents reach shared decisions and continue coordinated work when tasks are distributed or some agents cannot be trusted to behave correctly.

Skill for Claude CodeCodex

Part of the claude-flow plugin — 134 skills, 46 commands, 11 agents, 4 hooks shipped together

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.

agentmods
npx agentmods add skills/proffesor-for-testing/agentic-qe/hive-mind
Any agent
npx skills add proffesor-for-testing/agentic-qe --skill hive-mind
Clone the repo
git clone --depth 1 https://github.com/proffesor-for-testing/agentic-qe

Made for: Claude Code, Codex.

Or install claude-flow, the plugin that ships this one along with the rest of its 134 skills, 46 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

README.md
[![agentmods](https://agentmods.dev/badge/skills/proffesor-for-testing/agentic-qe/hive-mind.svg)](https://agentmods.dev/skills/proffesor-for-testing/agentic-qe/hive-mind)
Your own site
<a href="https://agentmods.dev/skills/proffesor-for-testing/agentic-qe/hive-mind"><img src="https://agentmods.dev/badge/skills/proffesor-for-testing/agentic-qe/hive-mind.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00061 $0.00433
Opus 5 $0.00030 $0.00217
Sonnet 5 $0.00012 $0.00087
Haiku 4.5 $0.00006 $0.00043

Measured 2d ago against content hash 4edb7cca7df5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

hive-mind 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 2d 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

This is a copy

100% identical to hive-mind — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/ruflo/.agents/skills/hive-mind/SKILL.md · 66 lines

What it actually says

Hive-Mind Skill

Purpose

Byzantine fault-tolerant consensus and distributed swarm coordination.

When to Trigger

  • Multi-agent distributed tasks
  • Fault-tolerant operations needed
  • Collective decision making
  • Complex coordination patterns

Topologies

Topology Description Use Case
hierarchical Queen controls workers Default, anti-drift
mesh Fully connected peers Research, exploration
hierarchical-mesh Hybrid Recommended for complex
adaptive Dynamic based on load Auto-scaling

Consensus Strategies

Strategy Tolerance Use Case
byzantine f < n/3 faulty Untrusted environment
raft f < n/2 faulty Leader-based, consistent
gossip Eventual Large scale, availability
crdt Conflict-free Concurrent updates
quorum Configurable Tunable consistency

Commands

Initialize Hive-Mind

npx claude-flow hive-mind init --topology hierarchical-mesh --consensus raft

Spawn Queen

npx claude-flow hive-mind spawn --role queen --name coordinator

Check Consensus Status

npx claude-flow hive-mind consensus --status

View Sessions

npx claude-flow hive-mind sessions --active

Best Practices

  1. Use hierarchical for coding tasks (anti-drift)
  2. Use raft consensus for consistency
  3. Keep agent count under 8 for coordination
  4. Run frequent checkpoints
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. 2d ago First seen · 66 lines · 61 tokens per session scan A 4edb7cca7df5

Subscribe to this mod's changes

hive-mind is a skill published in the GitHub repository proffesor-for-testing/agentic-qe (474 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 433 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hive-mind, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

tooluniverse-drug-research

Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…

mims-harvard/ToolUniverse · 71 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens

gh-bulk-issues

Orchestrate parallel Mastra Code headless instances to debug and fix multiple GitHub issues simultaneously.

mastra-ai/mastra · 25 tokens

qa-investigation

Investigate a specific test failure to its root cause and document the why. Detects whether a failing test is flaky (intermittent) or a deterministic bug during reproduction. Use when a test fails and you need the real cause, not just to make it green. Execution layer, not strategy review. Keywords: flaky test…

fugazi/test-automation-skills-agents · 94 tokens