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/selvarajmurugesan90/ops-engineering-skillsnpx agentmods add skills/selvarajmurugesan90/ops-engineering-skills/cloud-data-warehouse-operations-snowflake-bigquery-redshiftWrote 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/selvarajmurugesan90/ops-engineering-skills/cloud-data-warehouse-operations-snowflake-bigquery-redshift)<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/cloud-data-warehouse-operations-snowflake-bigquery-redshift"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/cloud-data-warehouse-operations-snowflake-bigquery-redshift/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/selvarajmurugesan90/ops-engineering-skills/cloud-data-warehouse-operations-snowflake-bigquery-redshift"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/cloud-data-warehouse-operations-snowflake-bigquery-redshift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00137 | $0.04378 |
| Opus 5 | $0.00068 | $0.02189 |
| Sonnet 5 | $0.00027 | $0.00876 |
| Haiku 4.5 | $0.00014 | $0.00438 |
Grade A, and why
cloud-data-warehouse-operations-snowflake-bigquery-redshift 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 12d 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Data Warehouse Operations: Snowflake, BigQuery, and Redshift
Purpose
Snowflake, BigQuery, and Redshift solve the same problem — running analytical SQL over very large datasets without managing physical servers — but with materially different billing models and scaling knobs, which means "tuning performance" and "controlling cost" are almost the same operational activity in all three, just expressed through different levers: virtual warehouse size and auto-suspend in Snowflake, slot allocation and bytes-scanned pricing in BigQuery, and node type/count and workload management queues in Redshift. This skill covers the operational levers specific to each, plus the cost-control and query-performance discipline that generalizes across all three, so a team choosing between them (or operating more than one) has a single comparative reference instead of three disconnected vendor docs.
When to use
- Sizing a new Snowflake virtual warehouse, BigQuery reservation/slot commitment, or Redshift cluster for a new workload.
- The monthly warehouse bill has grown unexpectedly and needs attribution to specific workloads/queries before deciding what to cut.
- A query that used to run quickly has degraded, and the cause could be warehouse/slot contention, a bad query plan, or data growth.
- Configuring Snowflake multi-cluster warehouses, BigQuery reservation assignment, or Redshift WLM queues to isolate workloads (e.g. ETL vs. ad hoc BI) from starving each other.
- Evaluating which of the three (or a combination) fits a given workload's query pattern and team's operational preferences.
Prerequisites & environment
- Administrative access to the relevant warehouse's account-level
configuration:
ACCOUNTADMINor a role withMONITOR/warehouse management privileges in Snowflake; a GCP project with BigQuery Admin or Resource Manager access for slot/reservation configuration; an AWS account with Redshift cluster/parameter-group management permissions. - Query-history/billing visibility: Snowflake's
ACCOUNT_USAGEschema (orINFORMATION_SCHEMAfor shorter retention), BigQuery'sINFORMATION_SCHEMA.JOBSviews and Cloud Billing export, Redshift'sSTL_QUERY/SVL_QUERY_SUMMARYsystem tables or Redshift's query monitoring in the console — all three require this for any cost- attribution or slow-query diagnosis in this skill. - An understanding of the workload's actual query pattern (concurrent BI dashboard load vs. scheduled batch ETL vs. ad hoc analyst queries) before sizing anything — the right warehouse/slot/cluster size and concurrency-scaling configuration depends entirely on this, not on the data volume alone.
- For Redshift specifically: familiarity with whether the cluster uses legacy dense-compute/dense-storage nodes or RA3 nodes (RA3 separates compute from managed storage, which changes both scaling and cost characteristics materially compared to older node types).
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.
- 12d ago First seen · 370 lines · 137 tokens per session scan A 9cafaad0bfe3
cloud-data-warehouse-operations-snowflake-bigquery-redshift is a skill published in the GitHub repository selvarajmurugesan90/ops-engineering-skills (39 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 137 tokens to every session and 4,378 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.