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/nevaberry/nevaberry-plugins/apache-kafka-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill apache-kafka-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWrote 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/nevaberry/nevaberry-plugins/apache-kafka-knowledge-patch)<a href="https://agentmods.dev/skills/nevaberry/nevaberry-plugins/apache-kafka-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/apache-kafka-knowledge-patch.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 | $0.00010 | $0.02232 |
| Opus 5 | $0.00005 | $0.01116 |
| Sonnet 5 | $0.00002 | $0.00446 |
| Haiku 4.5 | $0.00001 | $0.00223 |
Grade A, and why
apache-kafka-knowledge-patch 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 3d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apache Kafka Knowledge Patch
Use this skill when upgrading, configuring, extending, or operating Apache Kafka and its clients, Kafka Streams, Kafka Connect, MirrorMaker, KRaft, share groups, or tiered storage. Inspect the project's actual broker, client, metadata, and Java versions before applying version-dependent advice.
Reference index
| Reference | Topics |
|---|---|
| upgrades-and-runtime.md | Safe release selection, KRaft upgrade gates, feature finalization, metadata downgrade limits, Java and logging migrations |
| brokers-and-storage.md | Broker configuration, ELR, coordinators, KRaft quorum, log cleaning, retention, tiered and remote storage |
| clients-groups-and-transactions.md | Producer, consumer, Admin, transactions, group protocols, share groups, client APIs |
| kafka-streams.md | Streams migrations, rebalance protocol, handlers, state stores, headers, metrics, RocksDB |
| connect-and-mirrormaker.md | Connect runtime and REST changes, plugin APIs and versions, converters, MirrorMaker 2 |
| security-observability-and-tools.md | OAuth and SASL, principal builders, JMX and telemetry, metric migrations, CLI option changes |
Upgrade safety first
Establish the cluster mode and floor
- Kafka brokers are KRaft-only. Migrate any ZooKeeper cluster before attempting a broker upgrade.
- Do not roll an old KRaft cluster directly when its software or metadata version is below 3.3. Move it to 3.9.x first.
- Before a 4.0 broker roll, require Kafka clients, Streams, and Connect at 2.1 or later; exactly-once Streams workloads require brokers 2.5 or later.
- Verify non-Apache client compatibility independently.
- Brokers, Connect, and Kafka tools require Java 17; clients and Streams require Java 11. Java 25 is supported by Kafka 4.2.
What ships with it
7 files 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.
- 3d ago First seen · 162 lines · 10 tokens per session scan A e191b66e548e
apache-kafka-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 2,232 once invoked, about $0.0001 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
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…