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 skills add christiangalsterer/documentation-plugin --skill kafka-integrationgit clone --depth 1 https://github.com/christiangalsterer/documentation-pluginWrote 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/christiangalsterer/documentation-plugin/kafka-integration)<a href="https://agentmods.dev/skills/christiangalsterer/documentation-plugin/kafka-integration"><img src="https://agentmods.dev/badge/skills/christiangalsterer/documentation-plugin/kafka-integration/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.
<a href="https://agentmods.dev/skills/christiangalsterer/documentation-plugin/kafka-integration"><img src="https://agentmods.dev/badge/skills/christiangalsterer/documentation-plugin/kafka-integration.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00080 | $0.01090 |
| Opus 5.5 | $0.00032 | $0.00436 |
| Sonnet 5.5 | $0.00016 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
kafka-integration 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 20d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kafka integration
Use this skill to reason about Kafka integration behavior and tradeoffs. It is
usable directly by a human or as domain guidance for another agent or skill.
For Kafka documentation, use this skill to establish and verify technical
content, then use tech-writer for document structure and writing conventions.
Workflow
- Identify the task and boundary. Determine whether the user needs a conceptual answer, design, implementation guidance, review, migration, or troubleshooting. Identify which applications, Kafka components, and downstream systems are in scope.
- Gather decision-relevant context. Establish requirements and constraints that could change the recommendation. Depending on the task, this may include broker and client versions, deployment or managed-service type, throughput, peak message size, latency, ordering scope, retention, delivery expectations, availability, and recovery objectives.
- Ask or proceed with assumptions. Ask concise questions only when a missing fact could materially change the answer. Otherwise, state assumptions and give a useful initial recommendation. Do not make users provide irrelevant details before answering a focused question.
- Trace the relevant message flow. Consider key and partition selection, producer acknowledgments and retries, broker replication, consumer assignment and offset commits, downstream side effects, and replay or recovery as applicable.
- Evaluate behavior under failure. Check the relevant failure cases, such as broker or zone loss, producer errors, consumer restarts and rebalances, poison records, schema incompatibility, downstream outages, lag growth, or replay. Use the references below when they apply.
- Recommend and qualify. Give a concrete recommendation, its tradeoffs, operational consequences, and validation steps. Separate confirmed facts from assumptions and risks. Qualify version- or service-specific claims.
- Adapt the output. Answer a focused question directly. For substantial design reviews or incidents, use the corresponding template if it helps; templates are optional and should be adapted to the request.
What ships with it
8 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.
- references/delivery-and-recovery.md 2.0 KB
- references/design-review.md 2.1 KB
- references/managed-services.md 1.1 KB
- references/partitioning-and-capacity.md 1.5 KB
- references/schemas-and-connectors.md 1.6 KB
- references/security-and-operations.md 1.5 KB
- templates/design-review.md 1.2 KB
- templates/troubleshooting.md 806 B
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.
- 20d ago First seen · 111 lines · 80 tokens per session scan A c060dcf2684b
kafka-integration is a skill published in the GitHub repository christiangalsterer/documentation-plugin (1 stars, last pushed 21d ago), licensed MIT. It adds 80 tokens to every session and 1,090 once invoked, about $0.0003 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 2026-10-07.
Other skills, from other repositories
api-design
Designs REST, GraphQL, and gRPC APIs (OpenAPI/schema/proto output) and reviews existing APIs for consistency, best practices, and breaking change risks.
architecture-design
Designs new systems from requirements: C4 model diagrams, service boundaries, API contracts, data design, failure modes, and cross-cutting concerns.
tools-unity-unitask
UniTask async/await patterns for Unity including cancellation, lifecycle binding, and coroutine interop.
tools-unity-vcontainer
VContainer dependency injection patterns for Unity including lifecycle management, scoped registrations, and common pitfalls.
wp-php-architecture
WordPress PHP architecture patterns — repository, service layer, DDD, SOLID, plugin/theme structure, CPT design, and anti-patterns. The definitive reference for professional WordPress PHP development.
qector-services
QECTOR service surfaces: REST (FastAPI / Flask), gRPC, MCP stdio, Prometheus metrics exporter (manual 17.4). Covers the Provisional status, the production checklist (manual 24.1), the request-size cap, the bearer-token check, the per-client rate limit, the strict decoder-type enum, the deployment modes (manual 24…