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 estuary/agent-skills --skill schema-field-selectiongit clone --depth 1 https://github.com/estuary/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/skills/estuary/agent-skills/schema-field-selection)<a href="https://agentmods.dev/skills/estuary/agent-skills/schema-field-selection"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/schema-field-selection/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/estuary/agent-skills/schema-field-selection"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/schema-field-selection.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 | $0.00067 | $0.01430 |
| Opus 5 | $0.00034 | $0.00715 |
| Sonnet 5 | $0.00013 | $0.00286 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
schema-field-selection 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 8d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Field Selection for Materializations
Control which fields are included or excluded in materializations using depth modes and field overrides.
Docs: https://docs.estuary.dev/guides/customize-materialization-fields/
When to Use
- Reduce table width by excluding unnecessary fields
- Include deeply nested fields that aren't selected by default
- Exclude sensitive fields from materializations (note: data still exists in the collection — for true PII protection, use redaction on the writeSchema instead)
- Override connector's default field recommendations
Procedure
Step 1: Pull the Materialization Spec
flowctl catalog pull-specs --name <materialization-name>
Step 2: Configure Field Selection
Add or modify the fields stanza in the binding:
bindings:
- source: tenant/your/collection
resource: { table: your_table }
fields:
recommended: true # Depth mode (see below)
require: # Object — explicitly include fields
deeply/nested/field: {}
another_field: {}
exclude: # Array — explicitly exclude fields
- sensitive_data
- debug_info
Note: require is an object (field: {}), exclude is an array (- field).
Note: Each connector marks certain fields as required — typically the root document (flow_document) and the collection-key components, and some connectors require additional fields (e.g., CDC-style materializations that depend on _meta/op). Attempting to exclude a connector-required field returns a LOCATION_REQUIRED / FIELD_REQUIRED constraint and the publish fails. The exact list comes from each connector's Validate response.
Depth Modes
The recommended setting controls how deeply nested fields are automatically selected. UI labels are in parentheses:
| Value | UI Label | Description |
|---|---|---|
0 |
Required Only | Selects only fields the connector marks required (root document + key components, plus any connector-specific required fields) |
1 |
Depth 1 (default) | Top-level scalar fields |
2 |
Depth 2 | Two levels of nesting |
true |
Unlimited Depth | All scalar fields at any depth |
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.
- 8d ago First seen · 127 lines · 67 tokens per session scan A 50ccd00750f5
schema-field-selection is a skill published in the GitHub repository estuary/agent-skills (7 stars, last pushed 18d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,430 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
cocoindex
This skill should be used when building data processing pipelines with CocoIndex, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change…
confluent-cloud-cdc-tableflow
Set up end-to-end Change Data Capture (CDC) pipelines on Confluent Cloud using Debezium source connectors, Flink for transformation, and Tableflow for data lake integration. Supports JSONSR, Avro, and Protobuf formats. Handles schemaless topics (plain JSON without SR) and multi-event topics. This skill handles the…
good-skill
Generate a Confluent Cloud topic creation script with idempotency checks. Use when the user asks to create a topic, provision topics, or write a create-topics.sh for Confluent Cloud. Do NOT trigger for self-managed Apache Kafka, schema registration, Terraform generation, or Kafka Streams topology authoring.
mysql-context
Pull compact MySQL field diffs into context via the mysql-context MCP binlog indexer. Use when the task depends on what changed in MySQL, recent database changes, a watched table, or a before/after row image. Do not use this to dump current table rows.
kafka-schema-registry
Scan a project to identify Kafka applications, extract schemas from data models, tag PII fields, generate Terraform for Confluent Schema Registry registration, and produce a migration report with rollout ordering. Use this skill when a user asks to analyze a folder or repo for Kafka usage, extract schemas, audit…
change-data-capture-admin
Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. NOT for writing an Apex change-event trigger — use apex/change-data-capture-apex. NOT for subscribing an external system over Pub/Sub or CometD — use…