Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ibm-self-serve-assets/building-blocksnpx agentmods add skills/ibm-self-serve-assets/building-blocks/data-streaming-confluentWrote 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/ibm-self-serve-assets/building-blocks/data-streaming-confluent)<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/data-streaming-confluent"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/data-streaming-confluent/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/ibm-self-serve-assets/building-blocks/data-streaming-confluent"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/data-streaming-confluent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 652 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 954 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 1006 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 655 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 847 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 881 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00068 | $0.09456 |
| Opus 5.5 | $0.00027 | $0.03782 |
| Sonnet 5.5 | $0.00014 | $0.01891 |
| Haiku 4.5 | $0.00007 | $0.00946 |
Grade A, and why
data-streaming-confluent 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 1mo 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 — 1,172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Streaming Confluent Skill
⚠️ Critical Configuration Requirements
MANDATORY: These configurations MUST be included in all generated solutions to prevent deployment failures.
1. Schema Registry Timing Dependency
Problem: Error: error reading Schema Registry Clusters: there are no SR clusters in environment
Solution: Schema Registry is auto-provisioned when Kafka cluster is created. MUST wait 60s before reading it.
# Wait for Schema Registry auto-provisioning
resource "time_sleep" "wait_for_schema_registry" {
create_duration = "60s"
depends_on = [confluent_kafka_cluster.main]
}
# Schema Registry data source with wait
data "confluent_schema_registry_cluster" "main" {
environment {
id = confluent_environment.main.id
}
depends_on = [time_sleep.wait_for_schema_registry]
}
2. API Key Environment Blocks
Problem: Error: Environment of the referred resource, if env-scoped
Solution: ALL API keys (Kafka, Flink, Schema Registry) MUST include environment block in managed_resource.
resource "confluent_api_key" "kafka_producer" {
owner { ... }
managed_resource {
id = confluent_kafka_cluster.main.id
# REQUIRED: Environment block
environment {
id = confluent_environment.main.id
}
}
}
3. Flink Table / Kafka Topic Ownership
Problem: Creating a Kafka topic with Terraform and then running CREATE TABLE IF NOT EXISTS for the same name can leave Flink using the already-inferred table (including raw VARBINARY columns when schemas are not registered yet). IF NOT EXISTS does not redefine the existing inferred table.
MANDATORY Solution: Pick exactly one ownership pattern for each Flink-visible stream:
- Default — Flink-owned typed stream: do not create that topic with
confluent_kafka_topic. Use FlinkCREATE TABLE; Confluent creates the backing topic and Schema Registry subjects. - Terraform-owned existing topic: create the topic and register compatible key/value schemas first, then use the inferred Flink table. Do not run
CREATE TABLEfor the same topic. UseALTER TABLEonly for supported metadata/watermark/property changes.
What ships with it
9 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.
- examples/CONNECTED-CARS-EXAMPLE.md 15 KB
- examples/IOT-MONITORING-EXAMPLE.md 19 KB
- examples/ORDER-ORCHESTRATION-EXAMPLE.md 19 KB
- README.md 14 KB
- references/flink-ml-forecast.md 14 KB
- templates/scripts/cleanup.sh 5.5 KB runs code
- templates/scripts/setup.sh 7.3 KB runs code
- templates/scripts/test.sh 5.4 KB runs code
- USAGE-GUIDE.md 19 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.
- 1mo ago Changed · +7 lines · +8 tokens per session 79cb7ac33d3d
- 2mo ago First seen · 1,165 lines · 60 tokens per session scan A 23574de17680
data-streaming-confluent is a skill published in the GitHub repository ibm-self-serve-assets/building-blocks (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 9,456 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 2026-08-30.
data-streaming-confluent compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| data-streaming-confluentibm-self-serve-assets/building-blocks | Skill | 28 | yesterday | Apache-2.0 | A | 68 | Claude Code, Codex |
| stripe-projectsNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 15 | Claude Code, Codex |
| alchemy-providerpingdotgg/t3code | Skill | 48k | yesterday | MIT | A | 153 | Claude Code, Codex |
| django-storages-s3Jeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 138 | Claude Code |
| websocket-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 36 | Claude Code |
| azure-eventhub-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 94 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |