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 j4flmao/agent-skills --skill event-drivengit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/event-driven)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/event-driven"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/event-driven/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.
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/event-driven"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/event-driven.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00144 | $0.01826 |
| Opus 5.5 | $0.00058 | $0.00730 |
| Sonnet 5.5 | $0.00029 | $0.00365 |
| Haiku 4.5 | $0.00014 | $0.00183 |
Grade A, and why
architecture-event-driven 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 today.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Event-Driven Architecture
Purpose
In EDA, services publish facts ("OrderPlaced") and other services react, so producers do not depend on consumers being available or even known. The price is eventual consistency, harder debugging, and the need for reliable publishing and idempotent consumption. This skill covers the architectural decisions that make EDA correct, not just decoupled.
Agent Protocol
Trigger
"event-driven", "EDA", "domain events", "pub/sub", "message broker choice", "dual-write problem", "outbox", "at-least-once", "event ordering", "event versioning", "choreography".
Input Context
- Business flows and which steps must be synchronous for the user.
- Throughput, ordering needs (per entity?), retention/replay needs.
- Existing infra (Kafka, RabbitMQ, cloud queues) and team experience.
- Consistency requirements and failure tolerance.
Output Artifact
Event catalog, broker/topology choice, delivery and idempotency design, schema/versioning policy, observability plan.
Response Format
Event: {Name}(past tense) v{n} Producer: {service} Consumers: {services}
Key (ordering): {aggregate id} Topic/queue: {name} Retention: {duration}
Publish: outbox -> {relay: CDC|poller} Delivery: at-least-once
Consumer: idempotent via {inbox table|natural upsert}; DLQ: {name}
Schema: {Avro|Protobuf|JSON Schema} compatibility={BACKWARD}
Completion Criteria
- Each message classified as event (fact) or command (request).
- No dual writes: outbox or CDC for publishing.
- Consumers idempotent; DLQ and retry policy defined.
- Ordering key chosen per aggregate where order matters.
- Trace context propagated in message headers.
Events vs Commands vs Queries
| Kind | Meaning | Addressed to | Can be rejected? | Transport |
|---|---|---|---|---|
| Event | "OrderPlaced" happened | Anyone interested | No (it is a fact) | Topic / pub-sub |
| Command | "ReserveStock" please | One owner | Yes | Queue or RPC |
| Query | "What is the stock?" | One owner | n/a | Sync RPC |
What ships with it
1 file 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.
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.
- today Changed · +105 lines · +144 tokens per session 0da153fc6bcb
- 1mo ago Changed · -499 lines · -132 tokens per session 1a7bcc1ec210
- 1mo ago First seen · 537 lines · 132 tokens per session scan A 688acd04f395
architecture-event-driven is a skill published in the GitHub repository j4flmao/agent-skills (34 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 1,826 once invoked, about $0.0006 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.
Other skills, from other repositories
kafka-expert
Expert-level Apache Kafka, event streaming, Kafka Streams, and distributed messaging. Use when the user mentions streaming, messaging, event driven, or Kafka Streams.
event-driven-architecture
Event-driven architecture patterns with event sourcing, CQRS, and message-driven communication. Use when designing distributed systems, microservices communication, or systems requiring eventual consistency and scalability.
event-driven-topology-selector
Choose between broker and mediator event-driven topologies based on workflow control needs, error handling requirements, and performance trade-offs. Use this skill whenever the user is designing an event-driven system, choosing between choreography and orchestration, deciding how events should flow between processors…
Kafka Event-Driven Testing
Test Kafka-based event-driven systems, producer and consumer integration tests with Testcontainers, schema compatibility gates, idempotency and ordering verification, dead-letter handling, and end-to-end event flow assertions.
architecture-paradigm-event-driven
Applies event-driven async messaging to decouple producers and consumers. Use when designing real-time or multi-subscriber systems needing loose coupling.
architecture-paradigm-serverless
Applies serverless FaaS patterns for event-driven workloads. Use when designing bursty workloads with minimal infrastructure and pay-per-execution cost model.