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.
npx skills add hoangatg/ai-agent-toolkit --skill message-queuesgit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/hoangatg/ai-agent-toolkit/message-queues)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/message-queues"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/message-queues.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00714 |
| Opus 5 | $0.00020 | $0.00357 |
| Sonnet 5 | $0.00008 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
message-queues 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Message Queues
Decouple everything. Process asynchronously. Scale independently.
1. Technology Selection
| Technology | Best For | Model |
|---|---|---|
| Kafka | High throughput, event streaming | Log-based |
| RabbitMQ | Complex routing, traditional MQ | Broker-based |
| AWS SQS | Managed, serverless | Queue |
| Redis Streams | Lightweight, already using Redis | Log-based |
| NATS | Lightweight, cloud-native | Pub/Sub |
| Google Pub/Sub | Managed, GCP ecosystem | Topic-based |
2. Pattern Selection
| Pattern | Use When |
|---|---|
| Point-to-Point | One producer, one consumer |
| Pub/Sub | One event, many consumers |
| Fan-Out | Broadcast to all consumers |
| Work Queue | Distribute work across workers |
| Request-Reply | Async request with response |
| Dead Letter Queue | Handle failed messages |
3. Kafka Patterns
| Concept | Purpose |
|---|---|
| Topics | Category of messages |
| Partitions | Parallelism unit |
| Consumer Groups | Scale consumers independently |
| Offset | Track consumption position |
| Compaction | Keep latest per key |
Partition Strategy
| Strategy | Use Case |
|---|---|
| Key-based | Order guarantee per entity |
| Round-robin | Even distribution |
| Custom | Business-specific routing |
4. Message Design
| Principle | Application |
|---|---|
| Schema | Use Avro/Protobuf, not raw JSON |
| Idempotent | Safe to process twice |
| Self-contained | Include all needed data |
| Versioned | Schema evolution support |
| Small | Reference large data, don't embed |
Message Structure
{
"id": "uuid",
"type": "OrderCreated",
"timestamp": "ISO-8601",
"source": "order-service",
"data": { ... },
"metadata": { "correlationId", "version" }
}
5. Reliability Patterns
| Pattern | Purpose |
|---|---|
| At-least-once | May duplicate, never lose |
| At-most-once | May lose, never duplicate |
| Exactly-once | Kafka transactions (complex) |
| Outbox pattern | DB + queue atomicity |
| Retry + DLQ | Handle poison messages |
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.
- 4d ago First seen · 108 lines · 40 tokens per session scan A 27beb3a6f7d0
message-queues is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 714 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 2026-09-03.
Other skills, from other repositories
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
api-design
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
api-design
You are the API Design Specialist, responsible for designing RESTful, GraphQL, or other API interfaces. You ensure APIs are well-designed, documented, versioned, and follow best practices.