behive-research

A connector to BeHive, a research engine that gathers information from many sources, extracts scored claims, links related entities, and produces cited reports.

In plain words
What is it for?
Use it for deep research missions, intelligence gathering, claim extraction, quality scoring, and knowledge-graph construction when a BeHive instance is available.
Why use it?
It helps organize large research tasks into source-backed claims and a reusable knowledge base.

Skill for Claude CodeCodex

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/qa10devteam/behive/hermes
Any agent
npx skills add qa10devteam/behive --skill hermes
Clone the repo
git clone --depth 1 https://github.com/qa10devteam/behive

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00057 $0.01577
Opus 5 $0.00028 $0.00788
Sonnet 5 $0.00011 $0.00315
Haiku 4.5 $0.00006 $0.00158

Measured 2d ago against content hash ed189a733948, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

behive-research scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:8091/health | jq .
integrations/hermes/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BeHive Deep Research

Overview

BeHive is a deep research engine that extracts structured, scored claims from any topic. Unlike simple web search, it:

  1. Decomposes topics into research axes
  2. Fetches 1000+ sources via 8-layer stealth drones (70+ APIs)
  3. Extracts typed claims with per-claim quality scores (0.0–1.0)
  4. Builds entity relationship graphs (Neo4j)
  5. Produces synthesized reports with inline citations

This skill connects Hermes Agent to a running BeHive instance.

When to Use

  • User says "research X deeply", "gather intelligence on Y", "find everything about Z"
  • User needs verified facts with sources, not LLM-generated summaries
  • User wants claims they can cite, filter by quality, or query later
  • User asks to build a knowledge base on a topic over time
  • User says "run a mission on X", "scale 100", "deep dive"

Don't Use For

  • Simple factual lookups (use web_search)
  • Single-page content extraction (use web_extract)
  • Real-time news (BeHive takes 5-15 min per mission)

Prerequisites

BeHive API running at http://localhost:8091 or configured endpoint.

Verify:

curl -s http://localhost:8091/health | jq .

If using MCP (recommended), configure in ~/.hermes/config.yaml:

mcp_servers:
  behive:
    url: http://localhost:8090/mcp
    transport: streamable-http

Quick Research (MCP)

If BeHive MCP is configured, use MCP tools directly:

mcp_behive_research_topic(request={"query": "NVIDIA GPU market 2025-2026", "depth": 3, "force": true})

Then poll:

mcp_behive_mission_status(job_id="<returned_id>")

Get report:

mcp_behive_get_report(job_id="<id>", format="markdown")

Search past knowledge:

mcp_behive_search_knowledge(query="NVIDIA revenue", limit=20)

Research via REST API (terminal)

Start a Mission

curl -s -X POST http://localhost:8091/research \
  -H "Content-Type: application/json" \
  -d '{"topic": "EU AI Act enforcement mechanisms 2026", "scale": 30, "depth": 3}' | jq .

Read the full file on GitHub · 188 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. 2d ago First seen · 188 lines · 57 tokens per session scan A ed189a733948

Subscribe to this mod's changes

behive-research is a skill published in the GitHub repository qa10devteam/behive (143 stars, last pushed 19d ago), licensed MIT. It adds 57 tokens to every session and 1,577 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens