AI Agent Skills by Confluent is a collection of skills for building Kafka producers, Flink applications, and real-time data-streaming pipelines. Developers use it with coding assistants when creating applications and pipelines on Confluent. The catalogue entries are its skills, plugin, and instruction.
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 instructions/confluentinc/agent-skills/claude-mdgit clone --depth 1 https://github.com/confluentinc/agent-skillsWrote 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/instructions/confluentinc/agent-skills/claude-md)<a href="https://agentmods.dev/instructions/confluentinc/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/confluentinc/agent-skills/claude-md.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 5.1 | $0.01219 | $0.01219 |
| Opus 5 | $0.00609 | $0.00609 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
agent-skills CLAUDE.md 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository purpose
This repo packages a collection of AI agent skills for streaming/data-platform work on Confluent (Kafka producers/consumers, Kafka Streams, Schema Registry, Flink-based CDC to Tableflow). It is distributed as:
- A Claude Code plugin via
.claude-plugin/(marketplaceconfluent-agent-skills, pluginstreaming-skills-plugin). - A Cursor plugin via
.cursor-plugin/. - The
npx skills add confluentinc/agent-skillsCLI for other agents.
The "code" in this repo is mostly markdown — skill prompts, reference material, and eval definitions. There is no application to build or run.
Skill anatomy
Every skill lives under skills/<skill-name>/ with this layout:
skills/<skill-name>/
├── SKILL.md # Frontmatter (name, description) + body. Description gates triggering.
├── evals/evals.json # Prompts + expectations used to score the skill
├── references/ # Lazy-loaded markdown the SKILL.md tells the agent to read on demand
└── scripts/ # (optional) shell helpers the skill can invoke
Architectural conventions to preserve when editing:
- Lazy-load references. SKILL.md bodies are deliberately short and route the agent to
references/<topic>.mdonly when needed. Do not inline the contents of reference files into SKILL.md, and do not have SKILL.md instruct the agent to read all references upfront — see the explicit warning at the top ofskills/kafka-streams-programming/SKILL.md. New reference files should be reachable from a decision/mode section in SKILL.md, not loaded preemptively. - The
description:field is the trigger. It must include positive trigger phrases and explicit "Do NOT trigger for…" exclusions where adjacent skills could fight over the same prompt (see the kafka-streams and CDC-tableflow descriptions for the pattern). When adding/renaming a skill, audit neighboring skills' descriptions for overlap. - Mode detection. Larger skills (e.g.
kafka-streams-programming) branch internally into Build / Architect / Debug modes. Keep that table-driven structure when extending — don't fork mode logic into separate skills.
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.
- 6d ago First seen · 80 lines · 1,219 tokens per session scan A f7a52a4707e5
agent-skills CLAUDE.md is an instructions file published in the GitHub repository confluentinc/agent-skills (54 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,219 tokens to every session, about $0.0061 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 instructions, from other repositories
mq-bridge-app AGENTS.md
Instructions for marcomq/mq-bridge-app, covering agents.md, project snapshot, current ui architecture, important recent behavior decisions and testing guidance.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
ai-mind AGENTS.md
AGENTS.md instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.
pi AGENTS.md
AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.