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/confluentinc/agent-skills/developing-kafka-python-clientnpx skills add confluentinc/agent-skills --skill developing-kafka-python-clientgit clone --depth 1 https://github.com/confluentinc/agent-skillsWhat 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 | $0.00075 | $0.08993 |
| Opus 5 | $0.00037 | $0.04496 |
| Sonnet 5 | $0.00015 | $0.01799 |
| Haiku 4.5 | $0.00007 | $0.00899 |
Grade A, and why
developing-kafka-python-client 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 2d 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Begin by announcing: "Using the Confluent Kafka Python Client skill to guide this project."
Confluent Kafka Python Client Creation
Generate a production-ready Python project for producing to and/or consuming from Kafka using confluent-kafka-python. Supports three target environments: Confluent Cloud (managed), Local Docker (open-source Kafka), and WarpStream (Kafka-compatible, object-storage-backed), and two producer styles: AsyncIO (non-blocking) and Synchronous (blocking). The generated code follows Confluent's best practices.
Step 1: Gather Requirements
Before generating any code, work through the questions below. Skip any question the user has already answered explicitly in their prompt — do not re-ask just for form's sake. For example, "build a producer and consumer on Confluent Cloud with an async producer" already answers #2, #3, and #4; only #1, #5, #6, #7, and #8 remain.
Mandatory confirmation gate — do not skip, even if the user answered every question. Before writing any file, you MUST send one message that:
- Recaps the answers you extracted as a short bulleted list (e.g., "Target: Confluent Cloud · Components: producer + consumer · Producer style: async · From scratch: yes").
- Asks any remaining open questions inline.
- Explicitly asks the user to confirm or correct before you proceed.
Then STOP and wait for the user's reply. Do not generate files in the same turn as the recap, and do not proceed on the assumption that a fully-specified prompt implies consent to generate immediately — the recap catches misinterpretations of the prompt and is required even when questions #1–#8 are all pre-answered. The only way to skip the gate is if the user has already confirmed the recap earlier in this conversation.
What ships with it
19 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.
- evals/evals.json 14 KB
- evals/files/existing_producer.py 267 B runs code
- references/common.py 2.4 KB runs code
- references/consumer_avro.py 3.4 KB runs code
- references/consumer.py 2.9 KB runs code
- references/docker-compose.yml 690 B
- references/multi-event-guide.md 3.3 KB
- references/order_events.schema.json 4.0 KB
- references/producer_avro_sync.py 4.1 KB runs code
- references/producer_avro.py 5.0 KB runs code
- references/producer_multi_event_sync.py 5.3 KB runs code
- references/producer_multi_event.py 6.1 KB runs code
- references/producer_sync.py 5.1 KB runs code
- references/producer.py 5.5 KB runs code
- references/readme-template.md 2.1 KB
- references/schema-generation-rules.md 1.9 KB
- references/test_project.py 19 KB runs code
- references/value.avsc 955 B
- references/warpstream-optimization.md 13 KB
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.
- 2d ago First seen · 450 lines · 75 tokens per session scan A 78f72714e8f1
developing-kafka-python-client is a skill published in the GitHub repository confluentinc/agent-skills (54 stars, last pushed 4d ago), licensed Apache-2.0. It adds 75 tokens to every session and 8,993 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.
Other skills, from other repositories
python-patterns
Python best practices including type hints, async patterns, testing, and project structure.
python-api
Look up the public API of a Python package against the installed version and cache what's worth keeping. Four shapes by question type: (0) cache hit under scratch/api/ / /; (1) inspect.signature + pydoc.renderdoc for a symbol; (2) dir / pkgutil.itermodules for a module surface; (3) WebSearch + WebFetch of versioned…
python-code-style
Owns Python code style for this stack: ruff for lint + format, numpydoc for docstrings. Three responsibilities — (1) place the project's ruff.toml from the bundled template once the stack and workspace are in place, (2) run ruff against any Python files Claude has just generated or edited, and (3) contextualize each…
loom-python
Python language expertise for idiomatic, production-quality code. Use for web frameworks (FastAPI, Django, Flask), data processing (pandas, numpy), ML patterns (sklearn, pytorch), async programming, type hints, pytest, packaging with uv/poetry, and linting with ruff/mypy/black.
loom-concurrency
Concurrency and parallelism patterns for multi-threaded and async code. Use when implementing async/await, parallel processing, thread safety, worker pools, channels, or debugging race conditions and deadlocks across Rust (tokio), Python (asyncio), TypeScript, and Go.
python-services
Python patterns for CLI tools, async concurrency, and backend services. Use when working with Python code, building CLI apps, FastAPI services, async with asyncio, background jobs, or configuring uv, ruff, ty, pytest, or pyproject.toml.