agent-hivemind: Command for Claude Code

.claude/commands/hivesink-init.md

hivesink-init is a command for Claude Code from lancejames221b/agent-hivemind. It costs 17 tokens per session (1,984 once invoked), scanned B, original, MIT.

A command for synchronising hAIveMind skills, documentation, and configuration files between a local workspace and a vault. It supports pulling changes down or pushing local changes up, similar to Git sync.

In plain words
What is it for?
Pulling or pushing all content, or only skills, docs, or configs, with interactive selection, dry runs, and personal or team scope choices.
Why use it?
It reduces manual copying when you need to share or restore agent instructions and settings across personal, team, or global scopes.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is lancejames221b/agent-hivemind's own configuration. It tells Claude Code how to work on agent-hivemind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-hivemind configures →

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/commands/hivesink-init.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.

agentmods badge for hivesink-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/lancejames221b/agent-hivemind/hivesink-init.svg)](https://agentmods.dev/commands/lancejames221b/agent-hivemind/hivesink-init)
Your own site
<a href="https://agentmods.dev/commands/lancejames221b/agent-hivemind/hivesink-init"><img src="https://agentmods.dev/badge/commands/lancejames221b/agent-hivemind/hivesink-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,984 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00017 $0.01984
Opus 5 $0.00009 $0.00992
Sonnet 5 $0.00003 $0.00397
Haiku 4.5 $0.00002 $0.00198

Measured 6d ago against content hash 173ced788463, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

hivesink-init scanned grade B with 1 finding 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 6d 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.

Fix: mkdir -p ~/.haivemind/vault && chmod 700 ~/.haivemind
.claude/commands/hivesink-init.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hivesink-init - Simple Vault Sync

Purpose

Simple bi-directional sync for hAIveMind content. Pull from vault to start fresh, push to vault to share your setup.

Syntax

hivesink-init <direction> [options]

Direction (Required)

  • down - Pull from vault to local (like git pull)
  • up - Push from local to vault (like git push)

Selection Options (Pick One)

  • --all - Sync everything without prompts
  • --interactive - Prompt for each type (default)
  • --skills - Only skill files (.claude/commands/*.md)
  • --docs - Only CLAUDE.md and AGENT.md
  • --configs - Only config files (.mcp.json, config/*.json)

Additional Options

  • --dry-run - Show what would sync without making changes
  • --scope <personal|team|global> - Choose vault scope (will prompt if not specified)

Vault Storage Locations

By Scope

  • personal: ~/.haivemind/vault/ - Your private vault
  • team: ~/.haivemind/team/<team_name>/ - Shared with team
  • global: Via hAIveMind MCP sync service - Entire collective

Structure

~/.haivemind/vault/
├── skills/           # .claude/commands/*.md files
│   ├── hv-sync.md
│   ├── remember.md
│   └── ...
├── docs/             # Documentation files
│   ├── CLAUDE.md
│   └── AGENT.md
├── configs/          # Configuration files
│   ├── mcp.json
│   └── sync-protocol.json
└── manifest.json     # Vault contents index

Examples

Fresh Start - Pull Everything

hivesink-init down --all

Pull all skills, docs, and configs from vault. No prompts.

Interactive Pull

hivesink-init down

Prompts: Which scope? What content types? Approve each?

Share Your Setup

hivesink-init up --all

Push your entire setup to vault for backup/sharing.

Just Get Skills

hivesink-init down --skills --scope personal

Pull only skill files from personal vault.

Preview Changes

hivesink-init down --all --dry-run

See what would be synced without making changes.

Interactive Flow

When run without --all, you'll see:

Read the full file on GitHub · 273 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. 6d ago First seen · 273 lines · 17 tokens per session scan B 173ced788463

Subscribe to this mod's changes

hivesink-init is a command published in the GitHub repository lancejames221b/agent-hivemind (7 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,984 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.