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/estuary/agent-skills/materialize-postgres-createnpx skills add estuary/agent-skills --skill materialize-postgres-creategit clone --depth 1 https://github.com/estuary/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 | $0.00064 | $0.01686 |
| Opus 5 | $0.00032 | $0.00843 |
| Sonnet 5 | $0.00013 | $0.00337 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
materialize-postgres-create 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PostgreSQL Materialization
Create a PostgreSQL materialization using flowctl to stream data from Estuary collections into PostgreSQL tables.
Applies to: materialize-postgres (all variants: vanilla, RDS, Aurora, Cloud SQL, Supabase, AlloyDB, Neon)
Step 0: Load Connector Documentation
Before proceeding, fetch the official connector docs for prerequisites, config reference, and setup instructions.
Load the docs page: https://docs.estuary.dev/reference/Connectors/materialization-connectors/PostgreSQL/
Use WebFetch to load this page. It covers:
- Prerequisites (user creation, permissions, schema setup)
- Full config property reference
- SSH tunnel configuration
- SSL configuration
- Advanced options (delta updates, hard deletes, sync schedule)
Search Kapa for tribal knowledge (if the Estuary MCP is configured):
Search kapa ai knowledge sources for "materialize postgres common issues"
If Kapa MCP is not configured, the user can set it up: https://docs.estuary.dev/features/mcp-integration/
This skill provides the flowctl workflow and troubleshooting that docs don't cover.
Step 1: Gather Requirements
Before writing any YAML, ask the user:
- Postgres variant? — Vanilla, RDS, Aurora, Cloud SQL, Supabase, AlloyDB
- Network path? — Direct connection (cloud-hosted with IP allowlist), SSH tunnel (private network/on-prem), or ngrok (local dev).
Connection poolers are NOT supported. If the user mentions Supabase, Neon, PgBouncer, or PgCat, warn them immediately:
- The connector uses session-level temporary tables and prepared statements that break with pooled connections.
- Supabase: Must use the Direct connection (
db.xxx.supabase.co:5432), not the pooler (xxx.pooler.supabase.com:6543). - Neon: Must use the non-pooler endpoint — remove
-poolerfrom the hostname.
- Non-default data plane? — Most users use the default. Ask if they need a non-default data plane.
- Target database and schema? — Database name, schema (default:
public) - Source collections? — Which Estuary collections to materialize
- SSL required? — Some cloud providers require SSL connections
- Hard deletes? — Off by default. Without it, deleted rows stay in the destination marked with
_meta/op: 'd'. Enable to physically remove them. - Delta updates? — Off by default. Switches from one-row-per-key (standard merge) to append-only. Use for event logs or history tables.
- Sync schedule? — Controls how often batches are written to the destination (default: 30 minutes,
0sfor real-time). Affects latency and destination compute cost.
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 · 194 lines · 64 tokens per session scan A 1395af55e92e
materialize-postgres-create is a skill published in the GitHub repository estuary/agent-skills (7 stars, last pushed 12d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,686 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
stream-processing-designer
Design a stream processing system for unbounded, continuously arriving data. Use when choosing a message broker (Kafka vs RabbitMQ), implementing change data capture (CDC) from PostgreSQL, MySQL, or MongoDB via Debezium or Maxwell, selecting window types for aggregation (tumbling, hopping, sliding, session), joining…
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…
target-connector
This skill should be used when creating a new target connector for CocoIndex to integrate with external systems. It provides guidance on implementing TargetHandler, TargetActionSink, and related types for declarative target state synchronization with change detection and automatic cleanup.
cocoindex-diagrams
This skill should be used when creating, editing, or reviewing inline SVG diagrams for the CocoIndex docs site (anything under docs/src/content/docs/). It encodes the component-based primitive system under docs/src/components/diagrams/, the palette + shape semantics, the preview-and-verify loop using headless Chrome…
upgrade-examples
This skill should be used when upgrading the cocoindex package version in all example pyproject.toml files. It uses regex-based sed commands to efficiently update version constraints across multiple files at once.
developing-kafka-python-client
Use when the user wants to build a Python Kafka producer or consumer, add Schema Registry to existing Python code, migrate from raw JSON to schema-backed serialization, or scaffold a confluent-kafka-python project for Confluent Cloud, local Docker, or WarpStream. Also use when user wants to optimize Python Kafka…