aio-watermill-kit

aio-watermill-kit is a skill for Claude Code from aiocean/claude-plugins. It costs 71 tokens per session (3,486 once invoked), scanned A, original, MIT.

A guide to using Watermill, a Go library that connects application code to message brokers and organizes message handlers and events.

In plain words
What is it for?
It is for setting up Go publishers and subscribers, message routers, middleware, CQRS flows, event sourcing, and integrations with Kafka, AMQP, NATS, Redis, or SQL.
Why use it?
It gives a structured way to build asynchronous services while accounting for repeated message delivery and different levels of messaging complexity.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the aio-watermill-kit plugin — 1 skill shipped together

Good fit It is for setting up Go publishers and subscribers, message routers, middleware, CQRS flows, event sourcing, and integrations with Kafka, AMQP, NATS, Redis, or SQL.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add aiocean/claude-plugins
Claude Code
/plugin install aio-watermill-kit

Made for: Claude Code.

Or install aio-watermill-kit, 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 aio-watermill-kit

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-watermill-kit/github.svg)](https://agentmods.dev/skills/aiocean/claude-plugins/aio-watermill-kit)
Your own site
<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-watermill-kit"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-watermill-kit/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 aio-watermill-kit

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-watermill-kit"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-watermill-kit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,486 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 $0.00071 $0.03486
Opus 5.5 $0.00028 $0.01394
Sonnet 5.5 $0.00014 $0.00697
Haiku 4.5 $0.00007 $0.00349

Measured 1mo ago against content hash 657db07d3567, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aio-watermill-kit 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 1mo 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.

plugins/aio-watermill-kit/skills/aio-watermill-kit/SKILL.md · 429 lines

How it starts

The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watermill — Event-Driven Go Applications

Watermill is a Go library for building event-driven applications. It provides a clean abstraction over message brokers with a three-tier API: low-level Publisher/Subscriber interfaces, a mid-level Router with middleware support, and a high-level CQRS component.

The library's core philosophy: at-least-once delivery with idempotent handlers. Every handler you write should safely handle receiving the same message twice.

Architecture Overview

┌─────────────────────────────────────────────────┐
│  CQRS (High-level)                              │
│  CommandBus, EventBus, Processors, Marshalers   │
├─────────────────────────────────────────────────┤
│  Router (Mid-level)                             │
│  Handlers, Middleware chains, Lifecycle mgmt    │
├─────────────────────────────────────────────────┤
│  Publisher / Subscriber (Low-level)             │
│  Kafka, AMQP, Redis, NATS, SQL, GoChannel...   │
└─────────────────────────────────────────────────┘

Choose the right tier:

  • Publisher/Subscriber — when you need raw control or simple publish/consume
  • Router — when you need middleware, multiple handlers, or message transformation (most common)
  • CQRS — when you want typed commands/events with automatic marshaling

Core Types

Message

The fundamental data unit. Immutable after publishing.

msg := message.NewMessage(watermill.NewUUID(), payload)
msg.Metadata.Set("correlation_id", corrID)

// Lifecycle: created → published → acked/nacked
// Router handles Ack/Nack automatically — don't call them manually in handlers

Fields:

  • UUID (string) — unique ID for tracing/dedup, use watermill.NewUUID() or watermill.NewULID()
  • Payload ([]byte) — message body, any format (JSON, Protobuf, etc.)
  • Metadata (message.Metadata) — key-value headers, correlation IDs, partition keys
  • Context — standard context.Context for cancellation and deadlines

Publisher & Subscriber

Read the full file on GitHub · 429 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 429 lines · 71 tokens per session scan A 657db07d3567

Subscribe to this mod's changes

aio-watermill-kit is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 28d ago), licensed MIT. It adds 71 tokens to every session and 3,486 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 2026-09-03.