mqtt-embedded-integration

mqtt-embedded-integration is a skill for Claude Code, Codex from easyzoom/aix-skills. It costs 40 tokens per session (651 once invoked), scanned A, original, MIT.

A guide for integrating MQTT, a messaging system where devices publish messages to topics and subscribe to receive them. It covers the embedded client, network connection, security, delivery settings, and reconnection.

In plain words
What is it for?
Use it to configure or debug MQTT connections, publishing, subscriptions, QoS, keepalive, retained messages, Last Will, broker authentication, TLS, offline buffering, and reconnects on embedded devices.
Why use it?
It helps distinguish network, TCP/TLS, MQTT session, topic, delivery, memory, and reconnect problems instead of treating every failure as a connection issue.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to configure or debug MQTT connections, publishing, subscriptions, QoS, keepalive, retained messages, Last Will, broker authentication, TLS, offline buffering, and reconnects on embedded devices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/easyzoom/aix-skills/mqtt-embedded-integration
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 easyzoom/aix-skills --skill mqtt-embedded-integration
Clone the repo
git clone --depth 1 https://github.com/easyzoom/aix-skills

Made for: Claude Code, Codex.

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 mqtt-embedded-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/easyzoom/aix-skills/mqtt-embedded-integration/github.svg)](https://agentmods.dev/skills/easyzoom/aix-skills/mqtt-embedded-integration)
Your own site
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/mqtt-embedded-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/mqtt-embedded-integration/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 mqtt-embedded-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/mqtt-embedded-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/mqtt-embedded-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 651 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 $0.00040 $0.00651
Opus 5 $0.00020 $0.00326
Sonnet 5 $0.00008 $0.00130
Haiku 4.5 $0.00004 $0.00065

Measured 10d ago against content hash 3d81de032eda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mqtt-embedded-integration 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/mqtt-embedded-integration/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MQTT Embedded Integration

Overview

Use this skill for MCU MQTT clients by separating network link, TCP/TLS transport, MQTT session state, topic design, QoS, keepalive, and reconnect policy. MQTT success requires more than one successful publish.

When To Use

Use this skill when:

  • The user wants MQTT on an MCU or embedded device.
  • The task involves MQTT connect, publish, subscribe, keepalive, QoS, Last Will, retained messages, broker auth, TLS, reconnect, or offline buffering.
  • The issue is connection drops, no messages, duplicate messages, memory growth, TLS failure, or reconnect storms.

Do not use this skill when basic IP connectivity is not working. Use lwip-integration or platform network debugging first.

First Questions

Ask for:

  • MQTT library/client and version.
  • Network stack, RTOS, transport, and whether TLS is used.
  • Broker address, port, auth method, and certificate model without asking for secrets.
  • Client ID, topics, QoS levels, keepalive, and reconnect policy.
  • Current logs, broker logs, packet capture, or error codes.
  • RAM budget and maximum payload size.

Integration Checklist

  1. Prove network first. Confirm DNS/IP, TCP connect, and broker reachability before MQTT debugging.

  2. Configure identity. Client ID must be unique and stable enough for the product.

  3. Bound payloads and buffers. Topic length, payload size, QoS queues, and offline buffers must fit RAM.

  4. Set keepalive and reconnect policy. Avoid reconnect storms; use backoff and clear session behavior intentionally.

  5. Add TLS deliberately. Validate time, CA storage, certificate chain, SNI, and heap usage.

  6. Verify broker behavior. Test subscribe, publish, QoS behavior, retained messages, and Last Will if used.

Common Failures

  • Two devices use the same client ID and kick each other off.
  • TLS fails because device time is invalid.
  • Keepalive too short for poor networks.
  • QoS 1 duplicates are not handled idempotently.
  • Offline queue grows without bounds.
  • Topic wildcards subscribe to too much traffic for MCU RAM.

Read the full file on GitHub · 85 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. 10d ago First seen · 85 lines · 40 tokens per session scan A 3d81de032eda

Subscribe to this mod's changes

mqtt-embedded-integration is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 651 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 2026-08-30.

Related

Other skills, from other repositories

container-home

Answer questions, assist with planning, and help with design decisions for Mick's off-grid shipping container lake home project. Trigger when the user mentions the container home, lake home, Stewart County, LBL, the expansion, solar system, septic permitting, or retirement property.

mickpletcher/AI-Skills · 57 tokens

digital-twin-sync

Synchronize construction digital twins with real-time data. Connect BIM models with IoT sensors, progress updates, and field data for live project visualization and monitoring.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 36 tokens

drone-site-survey

Process drone survey data for construction sites. Generate orthomosaics, DEMs, point clouds, calculate volumes, track progress, and integrate with BIM models for comparison.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 40 tokens

equipment-fleet-manager

Manage construction equipment fleet. Track utilization, maintenance, and assignments.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 18 tokens

json-parser

Parse and validate JSON data from construction APIs, IoT sensors, and BIM exports. Transform nested JSON to flat DataFrames.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 28 tokens

energy-efficiency

Audit a manufacturing energy management system for monitoring quality, cost optimization, and compliance. Triggers: building or reviewing industrial energy platforms, building management systems, or sustainability reporting tools.

tinh2/skills-hub-registry · 39 tokens