A read-only connection to Snowflake, a cloud data warehouse where organizations store structured business data. It lets an agent inspect schemas and query that data with SQL.

Use it to explore databases and tables, query revenue or operational metrics, check row counts and freshness, and validate how a metric is defined.

It avoids manually searching through business tables for figures and definitions. Read-only access also keeps reporting queries separate from changes to production data.

snowflake — Skill for Claude Code and Codex by iblai/enterprise-agents

Install

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.

Any agent

npx skills add iblai/enterprise-agents --skill snowflake

Clone the repo

git clone --depth 1 https://github.com/iblai/enterprise-agents

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/iblai/enterprise-agents/snowflake/github.svg)](https://agentmods.dev/skills/iblai/enterprise-agents/snowflake)

Your own site

<a href="https://agentmods.dev/skills/iblai/enterprise-agents/snowflake"><img src="https://agentmods.dev/badge/skills/iblai/enterprise-agents/snowflake/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/iblai/enterprise-agents/snowflake"><img src="https://agentmods.dev/badge/skills/iblai/enterprise-agents/snowflake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 623 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00034	$0.00623
Opus 5.5	$0.00014	$0.00249
Sonnet 5.5	$0.00007	$0.00125
Haiku 4.5	$0.00003	$0.00062

Measured 2mo ago against content hash 3cd29cdb8720, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

snowflake 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 2mo 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.

skills/snowflake/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Snowflake

What it is

Snowflake is the leading cloud data warehouse platform, used by enterprise data and analytics teams as the central repository for structured business data. In this segment the data analysis agent uses Snowflake to run ad-hoc SQL queries, retrieve metric snapshots, and explore data model lineage. All access is read-only, routed through a dedicated reporting warehouse to avoid impacting production workloads.

When to use this skill

Running a SQL query to answer a business question about revenue, headcount, or operational KPIs
Exploring available databases, schemas, and tables before constructing a query
Fetching query results to populate a report or dashboard narrative
Checking table row counts and last-updated timestamps to assess data freshness
Validating a metric definition against the underlying table structure

Credentials

This skill authenticates using variables from ~/.openclaw/.env (template: .env.example at the config root). Required variables:

SNOWFLAKE_ACCOUNT - account identifier (e.g. myorg-myaccount)
SNOWFLAKE_USER - service account username
SNOWFLAKE_PASSWORD - service account password (or use key-pair; see Notes)
SNOWFLAKE_WAREHOUSE - virtual warehouse to use for query execution
SNOWFLAKE_DATABASE - default database context
SNOWFLAKE_SCHEMA - default schema context
SNOWFLAKE_ROLE - role to assume (should be a read-only reporting role)

Key operations

POST /api/v2/statements - execute a SQL statement via the Snowflake SQL REST API
GET /api/v2/statements/{statementHandle} - poll for async query results
SHOW DATABASES - list available databases
SHOW SCHEMAS IN DATABASE {db} - list schemas
SHOW TABLES IN SCHEMA {db}.{schema} - list tables with metadata

Notes

Always use a dedicated read-only role; never grant ACCOUNTADMIN or SYSADMIN to the service account.
Set QUERY_TAG on each session to identify agent-generated queries in the query history for auditing.
Credit consumption depends on warehouse size; use XS or S warehouse for reporting queries.
Key-pair authentication is preferred over password for production; store private key path separately.
Results larger than 10 MB are returned via pre-signed S3/GCS/Azure URLs in the REST API response.

Read the full file on GitHub · 42 lines

Changes

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.

2mo ago First seen · 42 lines · 34 tokens per session scan A 3cd29cdb8720

Subscribe to this mod's changes

snowflake is a skill published in the GitHub repository iblai/enterprise-agents (13 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 623 once invoked, about $0.0001 per session on Opus 5.5. 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.

Analytics and metrics Databases agentic-ai ai-agents anthropic claude conversational-ai employee-experience

snowflake next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
snowflakeiblai/enterprise-agents	Skill	13	5mo ago	MIT	A	34	Claude Code, Codex
postgresql-table-designwshobson/agents	Skill	42k	yesterday	MIT	A	37	Claude Code
sql-optimization-patternswshobson/agents	Skill	42k	yesterday	MIT	A	44	Claude Code
event-store-designwshobson/agents	Skill	42k	yesterday	MIT	A	33	Claude Code
cqrs-implementationwshobson/agents	Skill	42k	yesterday	MIT	A	35	Claude Code
projection-patternswshobson/agents	Skill	42k	yesterday	MIT	A	36	Claude Code
data-analytics-engineeringvasilyu1983/AI-Agents-public	Skill	101	21d ago	MIT	A	40	Claude Code, Codex