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 materialize-clickhouse-creategit 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/materialize-clickhouse-create)<a href="https://agentmods.dev/skills/estuary/agent-skills/materialize-clickhouse-create"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/materialize-clickhouse-create/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/materialize-clickhouse-create"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/materialize-clickhouse-create.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 | $0.00064 | $0.03249 |
| Opus 5 | $0.00032 | $0.01625 |
| Sonnet 5 | $0.00013 | $0.00650 |
| Haiku 4.5 | $0.00006 | $0.00325 |
Grade A, and why
materialize-clickhouse-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 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create ClickHouse Materialization
Create a ClickHouse materialization using flowctl to stream data from Estuary collections into ClickHouse tables.
Applies to: materialize-clickhouse (self-hosted and ClickHouse Cloud)
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/ClickHouse/
Use WebFetch to load this page. It covers:
- Prerequisites (user creation, database and system table permissions)
- Full config property reference
- SSL configuration (sslmode: disable, require, verify-full)
- ReplacingMergeTree engine details and FINAL directive usage
- Advanced options (delta updates, hard deletes)
Search Kapa for tribal knowledge (if the Estuary MCP is configured):
Search kapa ai knowledge sources for "materialize clickhouse 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:
- ClickHouse deployment? — Self-hosted or ClickHouse Cloud
- Address? —
host[:port]. Default port is 9440 with TLS enabled (default) or 9000 with TLS disabled. The connector uses the Native protocol — not the HTTP interface on port 8123. - Target database? — Name of the ClickHouse database to materialize to
- Username and password? — Auth type is
user_password(the only supported auth method) - SSL mode? — Defaults to
verify-full. Options:disable,require,verify-full - Non-default data plane? — Most users use the default. Ask if they need a non-default data plane.
- Source collections? — Which Estuary collections to materialize
- Hard deletes? — Off by default (soft-delete via
_meta/opcolumn). Enable to insert tombstone rows (_is_deleted = 1) that ClickHouse uses to exclude rows from FINAL queries and eventually remove from storage. - Delta updates? — Off by default. When enabled per-binding, the table uses the
MergeTreeengine instead ofReplacingMergeTree. Every store is appended as-is with no deduplication. Use for event logs or history tables.
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 · 304 lines · 64 tokens per session scan A ebaf8560eff1
materialize-clickhouse-create is a skill published in the GitHub repository estuary/agent-skills (7 stars, last pushed 18d ago), licensed Apache-2.0. It adds 64 tokens to every session and 3,249 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…
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 CDC Apex trigger implementation (use change-data-capture-integration).
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…
pinecone
Managed vector DB for production RAG and search.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.