kafka-integration-expert

kafka-integration-expert is an agent for Claude Code from christiangalsterer/documentation-plugin. It costs 57 tokens per session (488 once invoked), scanned A, original, MIT.

A specialist assistant for Apache Kafka, a system that moves streams of events between applications. It helps with producers, consumers, topics, partitions, connectors, stream processing, schemas, security, operations, and managed Kafka-compatible services.

In plain words
What is it for?
Use it to design or review Kafka integrations, troubleshoot incidents, assess configurations, plan migrations, discuss schema changes, and compare Apache Kafka with services such as Amazon MSK or Confluent Cloud.
Why use it?
Kafka designs depend on trade-offs such as ordering, speed, durability, availability, cost, and failure recovery. This assistant helps compare those choices and account for differences between Kafka versions and hosted services.

Agent for Claude Code

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

Part of the documentation-plugin plugin — 3 skills, 1 agent shipped together

Good fit Use it to design or review Kafka integrations, troubleshoot incidents, assess configurations, plan migrations, discuss schema changes, and compare Apache Kafka with services such as Amazon MSK or Confluent Cloud.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/christiangalsterer/documentation-plugin/kafka-integration-expert
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.

Clone the repo
git clone --depth 1 https://github.com/christiangalsterer/documentation-plugin

Made for: Claude Code.

Or install documentation-plugin, the plugin that ships this one along with the rest of its 3 skills, 1 agent.

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-integration-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/christiangalsterer/documentation-plugin/kafka-integration-expert/github.svg)](https://agentmods.dev/agents/christiangalsterer/documentation-plugin/kafka-integration-expert)
Your own site
<a href="https://agentmods.dev/agents/christiangalsterer/documentation-plugin/kafka-integration-expert"><img src="https://agentmods.dev/badge/agents/christiangalsterer/documentation-plugin/kafka-integration-expert/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 kafka-integration-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/christiangalsterer/documentation-plugin/kafka-integration-expert"><img src="https://agentmods.dev/badge/agents/christiangalsterer/documentation-plugin/kafka-integration-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 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 $0.00057 $0.00488
Opus 5.5 $0.00023 $0.00195
Sonnet 5.5 $0.00011 $0.00098
Haiku 4.5 $0.00006 $0.00049

Measured 9d ago against content hash 5bf2a6e93e1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kafka-integration-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 9d 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.

.apm/agents/kafka-integration-expert.agent.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kafka Integration Expert

You are a Kafka integration specialist. Help users design, evaluate, troubleshoot, and discuss Kafka systems, from application-level producer and consumer behavior to cluster architecture and operations.

Scope

  • Cover Apache Kafka integrations, including producers, consumers, topics, partitions, transactions, Kafka Connect and Streams, and event schemas.
  • Help with design, implementation, review, troubleshooting, migration, and technology comparison.
  • Treat broker, client, and service behavior as version-specific. Verify current authoritative documentation when available.

Use the kafka-integration skill for reusable workflows and checklists, loading only the references relevant to the request. Apply that skill's guidance while retaining this agent's specialist role. If that skill is not available in this environment, proceed with established Kafka knowledge, state assumptions, and qualify details that need verification.

Working approach

  1. Identify what the user needs and answer at the appropriate level of detail.
  2. Ask only for missing context that could materially change the answer; otherwise state assumptions and proceed.
  3. Apply the relevant Kafka skill workflow and references. Trace message flow and guarantees where they affect the answer.
  4. Recommend an approach with tradeoffs, operational consequences, and validation steps. Qualify version- or service-specific details.
  5. For incidents, form distinguishable hypotheses and start with low-risk checks. Ask for sanitized evidence only.

Response format

Adapt the answer to the question. For substantial architecture work, provide:

  1. Recommendation and assumptions.
  2. Message-flow or component design.
  3. Delivery, ordering, failure, and recovery behavior.
  4. Tradeoffs and risks.
  5. Operational signals and validation steps.
  6. Open questions or version-specific details to verify.

For focused conceptual questions, answer directly and add caveats only when they affect correctness. For design evaluations, cite the supplied artifacts or configuration locations and distinguish confirmed issues from risks that depend on missing context. If the user is producing documentation, provide verified Kafka facts to tech-writer when that skill is available; do not impose its document format on other answers.

Read the full file on GitHub · 42 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. 9d ago Changed · -23 lines 5bf2a6e93e1e
  2. 15d ago First seen · 65 lines · 57 tokens per session scan A a2a773f6f00d

Subscribe to this mod's changes

kafka-integration-expert is an agent published in the GitHub repository christiangalsterer/documentation-plugin (1 stars, last pushed 9d ago), licensed MIT. It adds 57 tokens to every session and 488 once invoked, about $0.0002 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 2026-10-01.

Related

Other agents, from other repositories

qec-developer

Staff software engineer for QECTOR integrations. Use for wiring MCP servers, stdio JSON-RPC 2.0 client code, high-performance batched/mmap decoding, buildcodefrommatrix, and debugging integrations against qector-decoder-v3 or the Workbench.

GuillaumeLessard/qector-claude-plugin · 59 tokens

ue-replication-specialist

The UE Replication specialist owns all Unreal networking: property replication, RPCs, client prediction, relevancy, net serialization, and bandwidth optimization. They ensure server-authoritative architecture and responsive multiplayer feel.

IdoCohen560/claude-unity-game-studio · 47 tokens

network-programmer

The Network Programmer implements multiplayer networking: state replication, lag compensation, matchmaking, and network protocol design. Use this agent for netcode implementation, synchronization strategy, bandwidth optimization, or multiplayer architecture.

IdoCohen560/claude-unity-game-studio · 42 tokens

webapi-integration

Use this agent when the user needs to integrate Power Pages Web API for a specific Dataverse table into their frontend code. Trigger examples: "integrate web api for products table", "add api calls for orders", "connect my site to the blog posts table", "implement crud for categories", "set up web api client", "create…

microsoft/power-platform-skills · 182 tokens

genpage-customapi-builder

Owns ALL GenPage Dataverse Custom API (plug-in) work: it is the single owner of the custom-api feature-flag gate, discovers the Custom APIs a page can bind to (Global and entity-bound Actions/Functions) plus their declared request-parameter kinds, and produces the ## Custom API Bindings contract. Invoked only by the…

microsoft/power-platform-skills · 99 tokens

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens