What is agent-hivemind CLAUDE.md?

Repository instructions for hAIveMind, a shared memory and coordination server that lets multiple AI agents retain and exchange DevOps knowledge.

Storing and retrieving incident, deployment, monitoring, security, and runbook information, coordinating agents, and synchronizing infrastructure settings.

They describe how agents share infrastructure information, coordinate work, and manage secure team workspaces.

How lancejames221b/agent-hivemind configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lancejames221b/agent-hivemind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lancejames221b/agent-hivemind/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lancejames221b/agent-hivemind

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/instructions/lancejames221b/agent-hivemind/claude-md/github.svg)](https://agentmods.dev/instructions/lancejames221b/agent-hivemind/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lancejames221b/agent-hivemind/claude-md"><img src="https://agentmods.dev/badge/instructions/lancejames221b/agent-hivemind/claude-md/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/instructions/lancejames221b/agent-hivemind/claude-md"><img src="https://agentmods.dev/badge/instructions/lancejames221b/agent-hivemind/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,122 This file is loaded in full into every session.

When invoked 6,122 The same file — it is already loaded in full.

Security scan B 2 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.06122	$0.06122
Opus 5.5	$0.02449	$0.02449
Sonnet 5.5	$0.01224	$0.01224
Haiku 4.5	$0.00612	$0.00612

Measured 2mo ago against content hash 431cfc8f6f85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agent-hivemind CLAUDE.md scanned grade B with 2 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 2mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt-get install redis-server

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8899/api/status

CLAUDE.md · 636 lines

How it starts

The opening of the file, as written. The whole thing — 636 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - ClaudeOps hAIveMind DevOps Memory System

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

ClaudeOps hAIveMind Overview

ClaudeOps is a hAIveMind - a centralized multi-agent DevOps memory MCP (Model Context Protocol) server that enables multiple Claude agents to collaborate on DevOps tasks across your entire infrastructure. The system provides persistent memory storage, real-time synchronization, agent coordination, and infrastructure management capabilities.

hAIveMind Features:

Collective Intelligence: Claude agents share knowledge, delegate tasks, and coordinate responses across infrastructure
Teams & Vaults: Secure collaborative workspaces with encrypted secret storage and role-based access control
Operating Modes: Solo, Vault, and Team modes for context-aware memory storage and retrieval
Infrastructure Configuration Sync: SSH configs, service configs, and other critical DevOps assets synchronized across the network
DevOps Memory Categories: Specialized storage for infrastructure, incidents, deployments, monitoring, runbooks, and security
Real-Time Collaboration: Agents broadcast discoveries, query each other's knowledge, and coordinate autonomous responses
Distributed Storage: ChromaDB for vector storage, Redis for caching, with conflict resolution via vector clocks
Token-Optimized Format (v2): Auto-teaches optimal compression on first memory access - 60-80% token reduction

Token-Optimized Format System (v2)

The memory system automatically teaches Claude the optimal format on first memory access each session:

Format Guide (injected automatically):

Symbols: → (flow) | (or) ? (opt) ! (req) :: (type)
Tables > prose: | key | val |
Refs: [ID]: define → use [ID]
Compact: auth(key) → search(q) → JSON

How it works:

First search_memories, retrieve_memory, or get_recent_memories call includes _haivemind_meta.format_guide
All stored memories are tagged with format_version: v2
Legacy verbose memories are flagged with legacy_content_detected: true
Use get_format_guide tool for detailed format reference

Read the full file on GitHub · 636 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.

2mo ago First seen · 636 lines · 6,122 tokens per session scan B 431cfc8f6f85

Subscribe to this mod's changes

agent-hivemind CLAUDE.md is an instructions file published in the GitHub repository lancejames221b/agent-hivemind (7 stars, last pushed 3mo ago), licensed MIT. It adds 6,122 tokens to every session, about $0.0245 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

agent-hivemind CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-hivemind CLAUDE.mdlancejames221b/agent-hivemind	Instructions file	7	3mo ago	MIT	B	6,122	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-hivemind: Instructions file for Claude Code