hive-connect-team

hive-connect-team is a skill for Claude Code, Codex from Hivemind-OSS/Hivemind. It costs 80 tokens per session (1,382 once invoked), scanned A, original, Apache-2.0.

A setup guide for connecting coding agents or teammates to a running Hivemind server. It covers local connections, ngrok tunnels for remote access, SSH forwarding, access tokens, and MCP client registration.

In plain words
What is it for?
Use it to add local or remote agents, provision or revoke seats, expose the server through a tunnel, and generate the correct MCP connection command.
Why use it?
It removes the guesswork from choosing a connection method and sharing the server safely with another machine or agent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to add local or remote agents, provision or revoke seats, expose the server through a tunnel, and generate the correct MCP connection command.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hivemind-oss/hivemind/hive-connect-team
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 Hivemind-OSS/Hivemind --skill hive-connect-team
Clone the repo
git clone --depth 1 https://github.com/Hivemind-OSS/Hivemind

Made for: Claude Code, Codex.

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-connect-team

README.md
[![agentmods](https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-connect-team/github.svg)](https://agentmods.dev/skills/hivemind-oss/hivemind/hive-connect-team)
Your own site
<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-connect-team"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-connect-team/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.

agentmods 80×15 button for hive-connect-team

Your own site · 80×15
<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-connect-team"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-connect-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,382 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.
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 $0.00080 $0.01382
Opus 5 $0.00040 $0.00691
Sonnet 5 $0.00016 $0.00276
Haiku 4.5 $0.00008 $0.00138

Measured 9d ago against content hash e9db680aee99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hive-connect-team 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 9d 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.

skills/hive-connect-team/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hive-connect-team — connect agents & teammates

Register clients against a server that is already up (hive-bringup). Full reference: HIVE-ADMIN.md §2 & §3.

CLI resolve (once per shell): command -v hive >/dev/null 2>&1 || hive() { python3 -m hive.tools.cli "$@"; } — makes every hive … line below run on an uninstalled checkout (the CLI is stdlib-only; Windows shells: py -m hive.tools.cli <verb>; prerequisites: hive-bringup).

Pick the door

Who Door Token?
An agent on the server host loopback 127.0.0.1:8765 no
A teammate on another machine ngrok tunnel (recommended) or SSH forward tunnel: yes · SSH: no

hive connect always prints the correct ready-made claude mcp add line for the host's current posture (the tunnel line when NGROK_DOMAIN is set, else the loopback line).

Local agent (tokenless)

hive connect
claude mcp add --transport http hive http://localhost:8765/mcp
  1. Free ngrok account → set both in .env (a plain hive up never exposes anything; --tunnel fail-fasts if either is missing):

    NGROK_AUTHTOKEN=...           # from the ngrok dashboard
    NGROK_DOMAIN=your.ngrok.app   # your account's static domain (stable URL)
    
  2. Start the tunnel sidecar and mint a seat:

    hive up --tunnel              # starts the ngrok sidecar; forwards https://<domain>/mcp
    hive token alice-laptop       # prints the token ONCE — hand over via a secret manager
    
  3. The teammate registers (the exact line hive connect prints once NGROK_DOMAIN is set):

    claude mcp add --transport http hive https://<your-domain>/mcp \
      --header "Authorization: Bearer <seat-token>"   # replace <seat-token> with the seat's token
    

    TLS terminates at the ngrok edge, so the token is encrypted in transit.

    This line bakes the URL and the seat token into the teammate's ~/.claude.json. If they also install the hive-connect-harness plugin, that registration wins over the plugin's own endpoint declaration — so HIVE_MCP_URL / HIVE_TOKEN in their profile become inert, and a rotated seat has to be applied by re-running this line rather than by editing the environment. Pick one route per teammate; that skill's Two routes to the endpoint section has the tradeoff.

Read the full file on GitHub · 96 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. 9d ago First seen · 96 lines · 80 tokens per session scan A e9db680aee99

Subscribe to this mod's changes

hive-connect-team is a skill published in the GitHub repository Hivemind-OSS/Hivemind (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,382 once invoked, about $0.0004 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 2026-08-31.