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.
curl -O https://raw.githubusercontent.com/fulminate-io/knowledge-mcp/main/.claude/skills/hive/SKILL.mdgit clone --depth 1 https://github.com/fulminate-io/knowledge-mcpWrote 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/fulminate-io/knowledge-mcp/hive)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/hive"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/hive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.01999 |
| Opus 5.5 | $0.00032 | $0.00800 |
| Sonnet 5.5 | $0.00016 | $0.00400 |
| Haiku 4.5 | $0.00008 | $0.00200 |
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 2mo 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 — 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
join→ Worker 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.
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.
- 2mo ago First seen · 178 lines · 79 tokens per session scan A bcc828030487
hive is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,999 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.