mq

mq is a skill for Claude Code from bababoi-bibilabu/agent-mq. It costs 42 tokens per session (525 once invoked), scanned A, original, MIT.

A message queue that lets separate AI coding sessions exchange messages, tasks, questions, replies, and status updates. It also keeps a list and history of connected agents.

In plain words
What is it for?
Use it to register agents, send work or questions, receive messages, inspect connected agents, and review communication history.
Why use it?
It gives agents a shared way to coordinate work when they are running in separate sessions. Messages are retrieved by polling rather than pushed automatically.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-mq plugin — 1 skill shipped together

Good fit Use it to register agents, send work or questions, receive messages, inspect connected agents, and review communication history.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bababoi-bibilabu/agent-mq/mq
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.

Any agent
npx skills add bababoi-bibilabu/agent-mq --skill mq
Clone the repo
git clone --depth 1 https://github.com/bababoi-bibilabu/agent-mq

Made for: Claude Code.

Or install agent-mq, the plugin that ships this one along with the rest of its 1 skill.

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 mq

README.md
[![agentmods](https://agentmods.dev/badge/skills/bababoi-bibilabu/agent-mq/mq/github.svg)](https://agentmods.dev/skills/bababoi-bibilabu/agent-mq/mq)
Your own site
<a href="https://agentmods.dev/skills/bababoi-bibilabu/agent-mq/mq"><img src="https://agentmods.dev/badge/skills/bababoi-bibilabu/agent-mq/mq/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.

agentmods 80×15 button for mq

Your own site · 80×15
<a href="https://agentmods.dev/skills/bababoi-bibilabu/agent-mq/mq"><img src="https://agentmods.dev/badge/skills/bababoi-bibilabu/agent-mq/mq.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 525 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 $0.00042 $0.00525
Opus 5 $0.00021 $0.00262
Sonnet 5 $0.00008 $0.00105
Haiku 4.5 $0.00004 $0.00052

Measured 10d ago against content hash bd276668e61a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mq 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 10d 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.

skills/mq/SKILL.md · 67 lines

What it actually says

agent-mq — Inter-Agent Message Queue

AI coding agents communicate through a message queue. Each agent has a name and can send/receive messages.

MCP Tools

  • mq_add(name, desc?, tool?) — add an agent
  • mq_send(target, message, sender, msg_type?, priority?, reply_to?) — send a message
  • mq_recv(name, msg_type?) — receive messages for an agent
  • mq_ls() — list agents
  • mq_history(limit?) — view message history
  • mq_login(token, server?) — login to server
  • mq_logout() — disconnect

Quick Start

mq_login(token: "your-uuid")
mq_add(name: "backend", desc: "working on API")
mq_send(target: "frontend", message: "API types changed", sender: "backend", msg_type: "task")
mq_recv(name: "backend")
mq_ls()

Message Types & Priority

Types: text (default), task, query, response, status Priority: low, normal (default), urgent

Message Format

{
  "id": "msg-uuid",
  "from": "sender-name",
  "to": "receiver-name",
  "payload": "message text",
  "type": "task",
  "priority": "normal",
  "ts": "2026-03-15T00:00:00Z"
}

Polling

agent-mq does not push messages. Set up periodic polling with CronCreate to check for new messages every 5 minutes:

Prompt: "Check for new messages with mq_recv(name: $AGENT_NAME) and process any tasks"

Key Properties

  • Name-based routing: send and receive by agent name
  • Consume-on-read: messages removed from inbox when read
  • UUID-based isolation: agents under the same token share a namespace; different tokens are invisible to each other
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. 10d ago First seen · 67 lines · 42 tokens per session scan A bd276668e61a

Subscribe to this mod's changes

mq is a skill published in the GitHub repository bababoi-bibilabu/agent-mq (2 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 525 once invoked, about $0.0002 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

sema-usage

Content-addressed vocabulary protocol via the sema MCP server. Use when working with shared vocabulary — searching, resolving, minting, and verifying meaning across agents and conversations.

emergent-wisdom/sema · 39 tokens

sema-mint

How to mint new sema patterns — the full pipeline from concept to content-addressed vocabulary entry. Covers required fields, dependency wiring, validation rules, and the hashing model.

emergent-wisdom/sema · 43 tokens

sema-seed

Seed the sema vocabulary by exploring random words. Pull a word from the system dictionary, think about it through the sema lens without forcing it into a pattern, then mint only if a genuinely useful and distinct pattern emerges. Use when the user asks to "seed", "expand", "grow", or "explore new patterns for" the…

emergent-wisdom/sema · 79 tokens

sema-ui

Launch the Sema web UI at localhost:3030 — interactive pattern browser with 3D graph, search, and live updates. Use when the user asks to "open the UI", "show the graph", or wants visual access to the vocabulary.

emergent-wisdom/sema · 57 tokens

agent-harness-fault-injection

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

sickn33/agentic-awesome-skills · 34 tokens

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens