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 skills add hive-intel/hive-sdk --skill hive-buildgit clone --depth 1 https://github.com/hive-intel/hive-sdkWrote 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.
[](https://agentmods.dev/skills/hive-intel/hive-sdk/hive-build)<a href="https://agentmods.dev/skills/hive-intel/hive-sdk/hive-build"><img src="https://agentmods.dev/badge/skills/hive-intel/hive-sdk/hive-build.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.02978 |
| Opus 5 | $0.00036 | $0.01489 |
| Sonnet 5 | $0.00015 | $0.00596 |
| Haiku 4.5 | $0.00007 | $0.00298 |
Grade B, and why
hive-build scanned grade B with 2 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 8d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
r = requests.post( "https://mcp.hiveintelligence.xyz/api/v1/execute", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
r = requests.post( How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hive-build — Integrate Hive Into App Code
Use this skill when the user is writing code that should call Hive at runtime (a TypeScript app, Python script, Next.js API route, Rust service, LangChain agent, Go cron job...).
If the user just wants live data in this chat, route to hive-query
instead. If they're adding Hive to an MCP-capable client, route to
hive-mcp. This skill is for "I'm writing code."
Integration path
- TypeScript / custom app default —
hive-mcp-client(npm install hive-mcp-client) - MCP transport —
https://mcp.hiveintelligence.xyz/mcp - REST fallback base —
https://mcp.hiveintelligence.xyz/api/v1 - REST execute —
POST /executewith{"tool": "...", "args": {...}} - REST catalog —
GET /tools?search=...&limit=... - Health —
GET https://mcp.hiveintelligence.xyz/health
Auth header on every request: Authorization: Bearer $HIVE_API_KEY.
Pattern by language
Python (sync — requests)
import os, requests
from typing import Any
def hive(tool: str, args: dict[str, Any] | None = None) -> dict[str, Any]:
r = requests.post(
"https://mcp.hiveintelligence.xyz/api/v1/execute",
headers={"Authorization": f"Bearer {os.environ['HIVE_API_KEY']}"},
json={"tool": tool, "args": args or {}},
timeout=30,
)
r.raise_for_status()
return r.json()
print(hive("get_price", {"ids": "bitcoin", "vs_currencies": "usd"}))
Python (async — httpx)
import os
import asyncio
import httpx
class HiveClient:
def __init__(self, key: str | None = None):
key = key or os.environ["HIVE_API_KEY"]
self._client = httpx.AsyncClient(
base_url="https://mcp.hiveintelligence.xyz",
headers={"Authorization": f"Bearer {key}"},
timeout=httpx.Timeout(30, connect=5),
limits=httpx.Limits(max_connections=32),
)
async def execute(self, tool: str, args: dict | None = None) -> dict:
r = await self._client.post(
"/api/v1/execute",
json={"tool": tool, "args": args or {}},
)
r.raise_for_status()
return r.json()
async def aclose(self):
await self._client.aclose()
async def briefing():
h = HiveClient()
try:
prices, tvl, oi = await asyncio.gather(
h.execute("get_price", {"ids": "bitcoin,ethereum"}),
h.execute("get_protocol_tvl", {}),
h.execute("get_open_interest", {"exchange": "binance"}),
)
return {"prices": prices, "tvl": tvl[:5], "oi": oi}
finally:
await h.aclose()
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.
- 8d ago First seen · 357 lines · 73 tokens per session scan B 49b5b08ce0bb
hive-build is a skill published in the GitHub repository hive-intel/hive-sdk (18 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,978 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…
add-service
Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.