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/j4flmao/agent-skillsnpx agentmods add skills/j4flmao/agent-skills/schema-registryWrote 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/j4flmao/agent-skills/schema-registry)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/schema-registry"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/schema-registry/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/j4flmao/agent-skills/schema-registry"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/schema-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 456 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00118 | $0.05620 |
| Opus 5 | $0.00059 | $0.02810 |
| Sonnet 5 | $0.00024 | $0.01124 |
| Haiku 4.5 | $0.00012 | $0.00562 |
Grade A, and why
data-schema-registry scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
cli: "curl -X POST https://registry:8081/compatibility/subjects/orders-value/versions \ How it starts
The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Schema Registry
Purpose
Design and deploy a schema registry with Avro/Protobuf/JSON Schema, compatibility enforcement, SerDe patterns, CI/CD integration, and governance for streaming and batch data.
Agent Protocol
Trigger
Exact user phrases: "Schema Registry", "Avro", "Protobuf", "schema evolution", "compatibility", "Confluent Schema Registry", "Apicurio", "serialization", "deserialization", "schema validation", "subject", "SerDe".
Input Context
- Streaming platform (Kafka, Pulsar, Kinesis)
- Serialization format preference (Avro, Protobuf, JSON Schema)
- Producers and consumers count and languages
- Schema governance maturity level
- CI/CD pipeline structure
- Existing schema management approach
Output Artifact
Schema registry architecture with format selection, compatibility strategy, SerDe configuration, deployment plan, and CI/CD governance integration.
Response Format
# Schema registry deployment
# Avro/Protobuf/JSON schema examples
# Compatibility rules per subject
# SerDe configuration (Kafka + batch)
# CI/CD schema enforcement pipeline
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Schema format selected with rationale
- Schema registry deployed and configured
- Schemas defined for all streaming topics
- Compatibility mode set per subject
- SerDe configured for producers and consumers
- CI/CD pipeline validates schema changes
- Schema governance documented with owner and review process
Max Response Length
350 lines of configuration.
Workflow
Step 1: Select Schema Format
| Format | Strengths | Weaknesses | Best For |
|---|---|---|---|
| Avro | Native Kafka/Confluent support, schema evolution, compact binary | Java-centric, limited JSON-like readability | Kafka streaming, Confluent ecosystem |
| Protobuf | Language-agnostic, fastest serialization, gRPC native | Schema evolution more strict, larger schemas | Cross-language, gRPC services |
| JSON Schema | Readable, widely understood, web-native | Larger payload, slower parsing | REST APIs, web frontends |
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/registry-setup.md 5.4 KB
- references/schema-evolution.md 4.6 KB
- references/schema-governance.md 1.9 KB
- references/schema-migration-strategies.md 4.3 KB
- references/schema-registry-evolution.md 15 KB
- references/schema-registry-integration-patterns.md 17 KB
- references/schema-registry-operations.md 4.0 KB
- references/schema-registry-tools.md 4.9 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.
- 9d ago First seen · 571 lines · 118 tokens per session scan A 9bf8c51fd3fd
data-schema-registry is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 6d ago), licensed MIT. It adds 118 tokens to every session and 5,620 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
avro
Apache Avro data serialization reference. Covers schema definition, primitive and complex types, logical types, schema evolution and compatibility rules, Confluent Schema Registry, Python/fastavro usage, Kafka integration, and Spark/Flink connectors.
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
architecture-paradigm-pipeline
Applies pipes-and-filters for sequential data transformations. Use when data flows through discrete stages like ETL, streaming analytics, or CI/CD pipelines.
relational-database-design
Designs or reviews a relational database schema for a given domain. Covers table structure, normalization, indexes, constraints, and migration strategy. Invoked when the user asks to design a schema, review a database structure, or optimize a data model.
data-engineer
Builds data infrastructure — ETL/ELT pipelines, data warehousing, stream processing, data quality, orchestration (Airflow/Dagster), and analytics engineering (dbt). Use when the user asks to build data pipelines, set up ETL/ELT workflows, design a data warehouse, configure stream processing, or implement analytics…
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…