hive-cli

A command-line interface for Hive, a service that provides queries and tools from a terminal. It supports sign-in, domain commands, JSON output, and diagnostics.

In plain words
What is it for?
Use it for one-off terminal queries, shell pipelines, scheduled briefings with cron, tool discovery, authentication checks, and local diagnostics.
Why use it?
It lets you use Hive in shell commands and scripts instead of manually repeating requests. JSON and jq support make results easier to filter and pass to other tools.

Skill for Claude CodeCodex

Part of the hive plugin — 17 skills, 1 MCP server 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/hive-intel/hive-sdk/hive-cli
Any agent
npx skills add hive-intel/hive-sdk --skill hive-cli
Clone the repo
git clone --depth 1 https://github.com/hive-intel/hive-sdk

Made for: Claude Code, Codex.

Or install hive, the plugin that ships this one along with the rest of its 17 skills, 1 MCP server.

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00097 $0.01312
Opus 5 $0.00048 $0.00656
Sonnet 5 $0.00019 $0.00262
Haiku 4.5 $0.00010 $0.00131

Measured 3d ago against content hash 778dca1bd117, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hive-cli 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 3d 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-cli/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hive-cli — Hive From the Terminal

Run Hive from a shell: one-off queries, jq pipelines, cron briefings, and diagnostics.

The Hive CLI lives in the hive-intelligence npm package; the executable name is hive. Package and binary names differ on purpose — the npm package also ships the stdio MCP server and bundled skills installer. One install, multiple agent entrypoints.

Bootstrap

If the user doesn't have the CLI installed:

# One-time install + auth
npx -y -p hive-intelligence@latest hive init --browser

# Or, install globally for repeated use
npm install -g hive-intelligence
hive auth login

init --browser runs the browser sign-in flow described in hive-build-onboarding.

Common commands

hive doctor                              # connectivity + auth check
hive status                              # plan, recent usage, key info
hive tools list                          # full live tool catalog
hive tools search <keyword>              # filter the catalog
hive tools info <tool-name>              # input schema for one tool
hive market price --ids bitcoin --vs usd # price query (domain subcommand)
hive defi tvl --protocol aave            # DeFi TVL query
hive watch defi protocols --interval 60  # re-run a domain command on an interval
hive uninstall --all                     # remove from every client

Domain subcommands map directly to Hive's category namespace: market, defi, portfolio, security, exchange, dex, wallet, nft, network, and search. Run hive --help for the full list and hive <domain> --help for a domain's subcommands.

JSON output and jq

Tool output is the envelope { ok, data, meta }. JSON is emitted automatically when stdout is not a TTY (when piped) or with --json; an interactive terminal prints human-readable output. Filter it two ways:

# Built-in --jq runs against the data payload directly (envelope-aware)
hive market price --ids bitcoin --vs usd --jq '.bitcoin.usd'

# Or pipe the --json envelope to external jq and read under .data
hive defi protocols --json | jq '.data[0].name'

Read the full file on GitHub · 140 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. 3d ago First seen · 140 lines · 97 tokens per session scan A 778dca1bd117

Subscribe to this mod's changes

hive-cli is a skill published in the GitHub repository hive-intel/hive-sdk (18 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 1,312 once invoked, about $0.0005 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 2026-08-30.