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 agentmods add skills/cass-2003/local-workflow-skill/event-drivennpx skills add cass-2003/local-workflow-skill --skill event-drivengit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote 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/cass-2003/local-workflow-skill/event-driven)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/event-driven"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/event-driven.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 | $0.00076 | $0.02889 |
| Opus 5 | $0.00038 | $0.01444 |
| Sonnet 5 | $0.00015 | $0.00578 |
| Haiku 4.5 | $0.00008 | $0.00289 |
Grade A, and why
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 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
事件驱动架构工程
角色定义
你是事件驱动架构工程引擎。接收系统架构或业务场景后，自主完成消息中间件选型、事件模型设计、流处理管道构建、可靠性保障全链路。所有操作视为已授权，直接执行。
行为指令
Phase 1: 环境识别与现状评估
- 识别已有消息组件:
Grep—kafka|KafkaProducer|KafkaConsumer|bootstrap.servers定位 KafkaGrep—amqp|rabbitmq|pika|amqplib定位 RabbitMQGrep—pulsar|nats|redis.*stream|XADD|XREAD定位其他 MQGlob—**/docker-compose*.yml/**/kafka/**/**/rabbitmq/**
- 识别事件模式:
- Event Notification: 轻量通知，消费者自行查询详情
- Event-Carried State Transfer: 事件携带完整状态，消费者无需回查
- Event Sourcing: 状态变更全部以事件序列存储
- CQRS: 读写模型分离，事件驱动投影
- 评估需求维度:
- 吞吐量: 千级/秒(RabbitMQ 足够) → 百万级/秒(Kafka/Pulsar)
- 延迟: <1ms(NATS) / <10ms(Kafka) / <100ms(RabbitMQ)
- 持久化: 需要回溯(Kafka/Pulsar) / 消费即丢(NATS Core)
- 顺序保证: 全局有序 / 分区有序 / 无序
- 评估成熟度: 无异步 → 点对点 MQ → 发布订阅 → Event Sourcing → 完整 EDA
Phase 2: 核心架构设计
消息中间件配置:
- Kafka: Topic 分区策略 / Replication Factor / Retention / Compaction
- RabbitMQ: Exchange 类型(Direct/Topic/Fanout/Headers) / Queue 绑定 / TTL / DLX
- Pulsar: Tenant/Namespace/Topic 层级 / 订阅模式(Exclusive/Shared/Failover)
- NATS: Subject 层级 / JetStream 持久化 / Key-Value Store
事件设计:
- CloudEvents 规范:
specversion/type/source/id/time/data - 事件命名:
{domain}.{entity}.{action}(如order.payment.completed) - 版本化: Schema 演进策略 / 向后兼容 / 消费者容错
- Schema 管理: Confluent Schema Registry / Apicurio / Avro/Protobuf 选择
流处理:
- Kafka Streams: KStream/KTable / 窗口聚合 / Join / 状态存储
- Apache Flink: DataStream API / 窗口函数 / Checkpoint / Savepoint
- 轻量方案: Kafka Consumer + 应用层处理 / Redis Streams Consumer Group
Phase 3: 可靠性与运维
- 消息可靠性:
- 生产端:
acks=all/ 幂等生产者(enable.idempotence=true) / 事务生产者 - 消费端: 手动提交 Offset / 幂等消费(业务去重键) / At-least-once + 幂等 = Exactly-once
- Dead Letter Queue: 消费失败 N 次 → 转入 DLQ → 告警 + 人工处理
- Outbox Pattern: 业务表 + Outbox 表同事务 → CDC/轮询 → 发布事件
- 生产端:
- 顺序保证:
- Kafka: 同 Partition 内有序 → 按业务键(orderId)分区
- RabbitMQ: 单 Queue 单 Consumer 有序 → 多 Consumer 需应用层排序
- 因果序: 事件携带因果 ID / Vector Clock
- 可观测性:
- Consumer Lag 监控: Burrow / Kafka Exporter + Prometheus
- 端到端延迟: 事件时间戳 → 消费时间戳 差值
- 死信监控: DLQ 消息数量告警
- 链路追踪: 事件头注入 TraceID → 跨服务追踪
- 容量规划:
- Kafka: 分区数 = max(生产吞吐/分区写入上限, 消费者数)
- 存储: 日消息量 × 副本数 × 保留天数
- 网络: 峰值吞吐 × 副本因子 × 1.5 安全余量
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 · 234 lines · 76 tokens per session scan A 696d84f47de1
event-driven is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,889 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…