knowledge-mcp: Skill for Claude Code

.claude/skills/hive/SKILL.md

hive is a skill for Claude Code from fulminate-io/knowledge-mcp. It costs 79 tokens per session (1,999 once invoked), scanned A, original, Apache-2.0.

A system for coordinating agents through a shared cloud work queue. Agents claim tasks addressed to their role, complete them, and report the results.

In plain words
What is it for?
Dispatching role-specific tasks, claiming available work, and sharing completed results between agents.
Why use it?
It lets agents on different machines pass work and bug reports to the right specialist without relying on a person to relay them.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is fulminate-io/knowledge-mcp's own configuration. It tells Claude Code how to work on knowledge-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything knowledge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fulminate-io/knowledge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fulminate-io/knowledge-mcp/main/.claude/skills/hive/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fulminate-io/knowledge-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for hive

README.md
[![agentmods](https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/hive.svg)](https://agentmods.dev/skills/fulminate-io/knowledge-mcp/hive)
Your own site
<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/hive"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/hive.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,999 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00079 $0.01999
Opus 5 $0.00039 $0.01000
Sonnet 5 $0.00016 $0.00400
Haiku 4.5 $0.00008 $0.00200

Measured 6d ago against content hash bcc828030487, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hive 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 6d 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.

.claude/skills/hive/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hive: $ARGUMENTS

For universal orchestration discipline (background spawning, user touch points, non-negotiation), reference /orchestrate. This skill is hive-specific.

A hive is a cloud work-queue that lets several agents — on the same machine or on different machines — coordinate by role. One agent puts a unit of work into the hive addressed to a role (@knowledge-developer); any worker holding that role claims it, does it, and reports the result back. The result is readable by whoever sent it.

Grounding use case: cross-machine capability teams. You run a knowledge-developer worker on one machine and an ml-developer worker on another. When the ml-developer hits a bug in a tool the knowledge-developer owns, it does not wait for a human to carry the report over — it sends the bug report to @knowledge-developer, and the knowledge-developer worker claims and fixes it autonomously.

You are dumb on purpose. The client daemon is your operating system — it monitors your work, keeps your claim alive, and removes you if your machine dies. You never heartbeat, never renew a lease, never track time. You only claim work and report when it's done. Everything else is the daemon's job.

The whole agent surface is the five hive ops: register, send, claim, ack, fail. Reads — who's registered, what's done, what's blocked — go through ordinary query / search, because everything lives in the graph. The hive is a hosted feature and requires login; a logged-out agent's hive calls fail loud.

Pick the mode from $ARGUMENTS:

  • starts with joinWorker mode (claim → work → report).
  • starts with dispatch (or you just want to send work and read results) → Coordinator mode.

Worker mode — /hive join <hive> as <role_1>, …, <role_N>

You are a worker holding one or more roles. You claim work addressed to any of your roles (or to the shared @queue), do it, and report the outcome.

Read the full file on GitHub · 178 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. 6d ago First seen · 178 lines · 79 tokens per session scan A bcc828030487

Subscribe to this mod's changes

hive is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,999 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens