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.
npx agentmods add skills/hive-intel/hive-sdk/hive-clinpx skills add hive-intel/hive-sdk --skill hive-cligit clone --depth 1 https://github.com/hive-intel/hive-sdkWhat 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 | $0.00097 | $0.01312 |
| Opus 5 | $0.00048 | $0.00656 |
| Sonnet 5 | $0.00019 | $0.00262 |
| Haiku 4.5 | $0.00010 | $0.00131 |
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.
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'
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.
- 3d ago First seen · 140 lines · 97 tokens per session scan A 778dca1bd117
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.
Other skills, from other repositories
agentmail
Use when an agent needs AgentMail CLI email inboxes.
fewer-permission-prompts
Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
taskflow
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting…
apple-reminders
Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.