agentleFS
Sign inStart free
hive-intelhive-intel/hive-sdk/skills/hive-setup/SKILL.md

hive-setup

Skill20 starsChanged 3 months agoMITView on GitHub

Use this skill to install, connect, sign in to, verify or remove Hive in an AI client or shell, or to get an API key for a server or script. Run it yourself with /hive-setup.

  • Reads credentials
  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. rllm-org/hive★ 216same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every data call needs a free account or an API key.

    line 18
  2. Very specific:

    Read references/clients.md and follow the block for the user's client (Claude Code, Claude, Cursor, VS Code, Windsurf, Gemini CLI, Codex, …

    line 35
  3. Distinctive:

    No browser to click means an API key:

    line 43
  4. Very specific:

    Ask the connected client: "What Hive tools do you have?" It should list nine tools (find_token, get_token_price, check_token_safety, …

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Hive setup

Hive is one hosted MCP server, a CLI and the hive skill:

  • MCP URL: https://mcp.hiveintelligence.xyz/mcp (Streamable HTTP).
  • Every data call needs a free account or an API key. Clients that support OAuth open a sign-in page on first use (GitHub, Google or an emailed code). The Free plan has 10,000 credits a month.

One command for every client on this machine

npx -y -p hive-intelligence@latest hive init --all --skip-verify

It registers the hosted URL in every detected client, installs the hive CLI globally (skip with --skip-global), and installs the Hive skills. Never run bare hive init from an agent: it is interactive and exits 1 in a shell without a terminal. Add --browser only when the user wants to sign the CLI in now.

One client

Read references/clients.md and follow the block for the user's client (Claude Code, Claude, Cursor, VS Code, Windsurf, Gemini CLI, Codex, ChatGPT, Grok, and the OpenAI Responses API). The URL is the same everywhere; only where it goes differs. Never put a placeholder Authorization header in a config.

Servers, scripts and CI

No browser to click means an API key:

  1. The user creates one at https://www.hiveintelligence.xyz/dashboard/keys.
  2. It goes in secret storage as HIVE_API_KEY, never in a prompt, a shared config, a repository or browser code.
  3. MCP clients send it as Authorization: Bearer <key>; the CLI reads it from the environment (hive research-token PEPE --json).

For the CLI: hive auth login signs in through the browser and stores the credential; HIVE_API_KEY in the environment also works. With no browser on the machine (SSH, CI, a container), hive auth login --device prints a code and a link. Give both to the person, who approves the code on any device; the CLI waits and stores the credential. hive auth login picks this on its own when it detects no browser.

Runtime status handling

  • missing_key or HTTP 401 on a data call: the client is not signed in. Reconnect the server in the client (it reopens the sign-in page) or set HIVE_API_KEY.
  • rate_limited with a quota message: the plan's monthly credits are spent; the message says when they reset.
  • Any other status: run hive doctor and follow its fix.

Verify

Ask the connected client: "What Hive tools do you have?" It should list nine tools (find_token, get_token_price, check_token_safety, research_token, analyze_wallet, market_positioning, market_overview, defi_yields, prediction_markets). Then ask "Is PEPE on Ethereum safe to buy, and what is it worth?" The answer should name GoPlus and CoinGecko with fetch times. From a shell:

hive doctor

Skills

npx skills add hive-intel/hive-sdk

installs hive (used automatically for crypto questions) and this setup skill.

Optional: project routing block

hive routing install adds a short block to the project's AGENTS.md or CLAUDE.md telling every agent turn to use Hive for live crypto data. Ask the user first; hive routing remove restores the file. hive routing decline records a no.

Remove

hive uninstall

removes Hive entries from client configs it can safely locate, prints the steps for clients configured in their own UI, and deletes the installed skills.

Stay current

The hosted server updates itself. A local stdio config must launch hive-intelligence@latest. Never write npx hive-mcp: that npm name belongs to an unrelated package. To update a global CLI:

npm install -g hive-intelligence@latest

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free