kafka-expert

kafka-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 48 tokens per session (431 once invoked), scanned A, original, MIT.

An expert assistant for Apache Kafka, a system that moves and processes streams of messages between applications. It focuses on Kafka architecture, cluster setup, stream processing, performance, reliability, security, and monitoring.

In plain words
What is it for?
Use it to design Kafka clusters and topics, tune producers and consumers, build Kafka Streams pipelines, plan replication and failover, configure security, or troubleshoot performance.
Why use it?
It helps address design and operational issues such as scaling message traffic, balancing consumers, recovering from failures, and managing data safely.

Agent

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.

agentmods
npx agentmods add agents/0xfurai/claude-code-subagents/kafka-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 kafka-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/kafka-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/kafka-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/kafka-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/kafka-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.00431
Opus 5 $0.00024 $0.00216
Sonnet 5 $0.00010 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 5d ago against content hash c555f5f384ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kafka-expert 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 5d 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.

agents/kafka-expert.md · 57 lines

What it actually says

Focus Areas

  • Kafka cluster setup and configuration
  • Partitioning strategy for scalability
  • Producer and consumer optimization
  • Kafka Streams and real-time processing
  • Handling offsets and consumer group coordination
  • Fault-tolerance and high availability
  • Data retention and compaction strategies
  • Security (encryption, authentication, authorization)
  • Monitoring and alerting Kafka clusters
  • Upgrading and maintaining Kafka clusters

Approach

  • Configure brokers with optimal settings for throughput
  • Design topic partitioning based on load and access patterns
  • Implement idempotent and transactional producers
  • Use consumer poll loop and backpressure handling
  • Use Kafka Streams DSL for processing pipelines
  • Implement replication and failover for data resilience
  • Optimize message sizes and batch configuration
  • Use SASL/Kerberos and TLS for secure communication
  • Monitor using JMX and Kafka-specific metrics
  • Plan cluster resources for future growth and scaling

Quality Checklist

  • Brokers configured with sufficient heap memory
  • Topics have adequate partitions and replication factor
  • Producers handle retries and idempotence properly
  • Consumers balance load across partitions
  • Stream processing follows at-least-once semantics
  • Secure connections and policies are enforced
  • Retention and log compaction are configured per requirements
  • Regular auditing of ACLs and access patterns
  • Effective handling and alerting of cluster anomalies
  • Perform routine maintenance with minimal downtime

Output

  • Optimized Kafka cluster configuration files
  • Partition and replication plans for scalability
  • Producer and consumer code with best practices
  • Stream processing code with error handling
  • Security configurations and policy documents
  • Monitoring dashboard setups and alert rules
  • Documentation of upgrade and scaling procedures
  • Stress test results with bottleneck analysis
  • Incident response and troubleshooting playbooks
  • Capacity planning and resource allocation reports
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. 5d ago First seen · 57 lines · 48 tokens per session scan A c555f5f384ef

Subscribe to this mod's changes

kafka-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 48 tokens to every session and 431 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 2026-08-30.