kafka-connector-review

kafka-connector-review is a skill for Claude Code from lensesio/agentic-engineering-for-apache-kafka. It costs 79 tokens per session (1,727 once invoked), scanned A, original, MIT.

A checklist for checking Apache Kafka Connect connector settings, which control how data moves into or out of Kafka. It uses the Lenses MCP server to inspect connectors, their tasks, and their configuration.

In plain words
What is it for?
Reviewing connector status, task health, converters, data transformations, error handling, dead-letter queues, and task counts; then producing a report with findings and suggested configurations.
Why use it?
It helps find settings that can make a connector fail or handle errors poorly, without checking each JSON or YAML option by hand.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the kafka-skills plugin — 10 skills shipped together

Good fit Reviewing connector status, task health, converters, data transformations, error handling, dead-letter queues, and task counts; then producing a report with findings and suggested configurations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lensesio/agentic-engineering-for-apache-kafka/kafka-connector-review
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 lensesio/agentic-engineering-for-apache-kafka --skill kafka-connector-review
Clone the repo
git clone --depth 1 https://github.com/lensesio/agentic-engineering-for-apache-kafka

Made for: Claude Code.

Or install kafka-skills, the plugin that ships this one along with the rest of its 10 skills.

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-connector-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/lensesio/agentic-engineering-for-apache-kafka/kafka-connector-review/github.svg)](https://agentmods.dev/skills/lensesio/agentic-engineering-for-apache-kafka/kafka-connector-review)
Your own site
<a href="https://agentmods.dev/skills/lensesio/agentic-engineering-for-apache-kafka/kafka-connector-review"><img src="https://agentmods.dev/badge/skills/lensesio/agentic-engineering-for-apache-kafka/kafka-connector-review/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-connector-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/lensesio/agentic-engineering-for-apache-kafka/kafka-connector-review"><img src="https://agentmods.dev/badge/skills/lensesio/agentic-engineering-for-apache-kafka/kafka-connector-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,727 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00079 $0.01727
Opus 5 $0.00039 $0.00864
Sonnet 5 $0.00016 $0.00345
Haiku 4.5 $0.00008 $0.00173

Measured 12d ago against content hash d4991cb04492, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kafka-connector-review 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 12d 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.

skills/kafka-connector-review/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kafka Connect Configuration Review

Reviews Kafka Connect connector configurations for common misconfigurations. Connectors are defined as JSON/YAML and are entirely language-agnostic.

Target environment: $ARGUMENTS

Workflow

Copy this checklist and track your progress:

Connector Review Progress:
- [ ] Step 1: List all connectors
- [ ] Step 2: Inspect each connector's configuration
- [ ] Step 3: Validate configurations against plugin schemas
- [ ] Step 4: Audit for common misconfigurations
- [ ] Step 5: Generate report
  1. List all connectors with status and task states
  2. Inspect each connector's configuration in detail
  3. Validate configurations against plugin schemas
  4. Audit for common misconfigurations
  5. Report findings with current and recommended configs

Step 1: List All Connectors

Use the Lenses MCP list_kafka_connectors tool to get all connectors with:

  • Connector name, class and type (source/sink)
  • Status (RUNNING, PAUSED, FAILED, UNASSIGNED)
  • Task states and count
  • Cluster info

Flag immediately:

  • Critical: Connectors in FAILED state
  • Critical: Tasks in FAILED state
  • Warning: Connectors in PAUSED state with no obvious reason

Expected output: List of all connectors with name, class, status and task states.

Validation: If no connectors are returned, report that no Connect cluster is configured and stop.

Step 2: Inspect Configurations

Use the Lenses MCP get_kafka_connector_target_definition tool to get the full configuration YAML for each connector.

Step 3: Validate Configurations

Use the Lenses MCP validate_connector_configuration tool to validate each connector's config against its plugin's schema. This catches:

  • Missing required configuration fields
  • Invalid configuration values
  • Type mismatches

Step 4: Audit Common Misconfigurations

Error Handling

  • Critical: errors.tolerance=all without errors.deadletterqueue.topic.name (silently drops messages)
  • Warning: Missing errors.tolerance (defaults to none, connector stops on any error)
  • Warning: Missing errors.log.enable=true (errors not logged)
  • Suggestion: Add errors.deadletterqueue.context.headers.enable=true for richer DLQ metadata

Read the full file on GitHub · 195 lines

Files

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.

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. 12d ago First seen · 195 lines · 79 tokens per session scan A d4991cb04492

Subscribe to this mod's changes

kafka-connector-review is a skill published in the GitHub repository lensesio/agentic-engineering-for-apache-kafka (57 stars, last pushed 21d ago), licensed MIT. It adds 79 tokens to every session and 1,727 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.

Related

Other skills, from other repositories

sdd-apply

Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.

Gentleman-Programming/gentle-ai · 0 tokens

fec-data-fetching

A frontend guide for handling data that comes from a server, including typed requests, caching, refreshing, pagination, and updates. Server state means data owned by an API rather than by a page’s local controls.

bovinphang/frontend-craft · 76 tokens

agent-java-reviewer

Expert Java code reviewer for Spring Boot and Quarkus projects. Automatically detects the framework and applies the appropriate review rules. Covers layered architecture, JPA/Panache, MongoDB, security, and concurrency. MUST BE USED for all Java code changes.

KunanonJ/ai-skills-hub · 56 tokens

agent-django-reviewer

Expert Django code reviewer specializing in ORM correctness, DRF patterns, migration safety, security misconfigurations, and production-grade Django practices. Use for all Django code changes. MUST BE USED for Django projects.

KunanonJ/ai-skills-hub · 47 tokens

fec-react-project-standard

A guide for organizing medium-sized or large React and TypeScript projects. It defines boundaries between pages, business features, shared components, hooks, services, state, APIs, and utilities.

bovinphang/frontend-craft · 101 tokens

agent-fastapi-reviewer

Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.

KunanonJ/ai-skills-hub · 34 tokens