asyncapi-generator

asyncapi-generator is a skill for Claude Code from pactflow/pactflow-agent-skills. It costs 205 tokens per session (2,948 once invoked), scanned A, original, MIT.

A code-analysis workflow that creates an AsyncAPI 3.x document for an event-driven service when no such document exists. AsyncAPI describes messages, topics, producers, and consumers rather than ordinary web requests.

In plain words
What is it for?
Use it to inspect a service codebase with ripwire and generate a valid AsyncAPI 3.x YAML file for its message producers and consumers.
Why use it?
Message routes are often spread across code, configuration, and environment variables, so they are easy to miss when documenting a service. The workflow gathers those details into a standard document and marks unresolved message shapes as stubs.

Skill for Claude Code

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

Part of the swagger-contract-testing plugin — 6 skills, 6 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to inspect a service codebase with ripwire and generate a valid AsyncAPI 3.x YAML file for its message producers and consumers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pactflow/pactflow-agent-skills/asyncapi-generator
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 pactflow/pactflow-agent-skills --skill asyncapi-generator
Clone the repo
git clone --depth 1 https://github.com/pactflow/pactflow-agent-skills

Made for: Claude Code.

Or install swagger-contract-testing, the plugin that ships this one along with the rest of its 6 skills, 6 agents, 2 hooks, 1 MCP server.

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 asyncapi-generator

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pactflow/pactflow-agent-skills/asyncapi-generator"><img src="https://agentmods.dev/badge/skills/pactflow/pactflow-agent-skills/asyncapi-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,948 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 $0.00205 $0.02948
Opus 5.5 $0.00082 $0.01179
Sonnet 5.5 $0.00041 $0.00590
Haiku 4.5 $0.00020 $0.00295

Measured 15d ago against content hash 0ee1f9b36107, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

asyncapi-generator 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 15d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (evals/fixtures/kafka-orders/src/consumer.js, evals/fixtures/kafka-orders/src/publisher.js, evals/fixtures/kafka-orders/src/topics.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/swagger-contract-testing/skills/asyncapi-generator/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AsyncAPI Generator

Generates an AsyncAPI 3.x spec by statically analysing a service codebase with ripwire. The spec may be incomplete (stub payloads where the shape can't be resolved), but it is always valid AsyncAPI 3.x and immediately usable as input to asyncapi-parser and Drift.

This is the async counterpart of oas-generator. The key difference: HTTP routes are declared in one place, but messaging topology is scattered — a topic name appears in a producer call, a consumer decorator, a config file and an env var. Most of the work is finding every send/receive site and resolving the channel name behind it.

Prerequisites: ripwire on PATH. If absent, see pact-coverage/references/install-ripwire.md. AsyncAPI 2.x is not supported by Drift, so always emit asyncapi: "3.0.0".

Read references/broker-patterns.md for grep patterns per broker/library. Read it in Step 2; don't load it earlier.


Step 1 — Identify broker and language

ripwire <service-root> --for="message producers and consumers publishing and subscribing to topics queues"

Confirm with dependency manifests (package.json, pom.xml/build.gradle, requirements.txt/ pyproject.toml, go.mod, Gemfile): kafkajs, spring-kafka, confluent-kafka, aws-sdk SNS/SQS clients, boto3, amqplib/pika, nats, google-cloud-pubsub, mqtt, ws.

A service often uses more than one broker; record all of them. If nothing messaging-related is found, tell the user — don't invent channels.


Step 2 — Find every send and receive site

Use the patterns in references/broker-patterns.md for the detected broker(s), passed to ripwire <root> --regex='<pattern>'. Use --regex, not --grep: --grep is a literal match, so a pattern with | alternation returns zero hits, and ripwire reports that zero as complete. If a search returns files="0", the root path is wrong or unindexed, not proof that nothing publishes. Run each applicable pattern and deduplicate. For every hit, note the enclosing symbol (in=) and classify it:

Read the full file on GitHub · 247 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. 15d ago First seen · 247 lines · 205 tokens per session scan A 0ee1f9b36107

Subscribe to this mod's changes

asyncapi-generator is a skill published in the GitHub repository pactflow/pactflow-agent-skills (7 stars, last pushed yesterday), licensed MIT. It adds 205 tokens to every session and 2,948 once invoked, about $0.0008 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 2026-10-02.