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 Snowflake-Labs/snowflake-ai-kit --skill snowflake-exploregit clone --depth 1 https://github.com/Snowflake-Labs/snowflake-ai-kitWrote 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/snowflake-labs/snowflake-ai-kit/snowflake-explore)<a href="https://agentmods.dev/skills/snowflake-labs/snowflake-ai-kit/snowflake-explore"><img src="https://agentmods.dev/badge/skills/snowflake-labs/snowflake-ai-kit/snowflake-explore/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/snowflake-labs/snowflake-ai-kit/snowflake-explore"><img src="https://agentmods.dev/badge/skills/snowflake-labs/snowflake-ai-kit/snowflake-explore.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 | $0.00036 | $0.00456 |
| Opus 5.5 | $0.00014 | $0.00182 |
| Sonnet 5.5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
snowflake-explore 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 16d 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.
What it actually says
Snowflake Explore
Discover and understand the data landscape in a Snowflake account.
When to use
- User asks "what data is available", "show me the tables", "what databases exist"
- User wants to inspect a table's columns, types, or sample data
- User needs to find a table by name or pattern
Discovery patterns
List databases:
SHOW DATABASES;
List schemas in a database:
SHOW SCHEMAS IN DATABASE my_db;
List tables in a schema:
SHOW TABLES IN SCHEMA my_db.my_schema;
Find tables by name pattern:
SHOW TABLES LIKE '%order%' IN ACCOUNT;
Describe a table (columns and types):
DESCRIBE TABLE my_db.my_schema.orders;
Full column metadata:
SELECT column_name, data_type, is_nullable, column_default
FROM my_db.INFORMATION_SCHEMA.COLUMNS
WHERE table_schema = 'MY_SCHEMA' AND table_name = 'ORDERS'
ORDER BY ordinal_position;
Preview data (always use LIMIT):
SELECT * FROM my_db.my_schema.orders LIMIT 5;
Find views:
SHOW VIEWS IN SCHEMA my_db.my_schema;
Find dynamic tables:
SHOW DYNAMIC TABLES IN SCHEMA my_db.my_schema;
Find stages (file storage):
SHOW STAGES IN SCHEMA my_db.my_schema;
Find streams (change tracking):
SHOW STREAMS IN SCHEMA my_db.my_schema;
Tips
- SHOW commands accept LIKE patterns:
SHOW TABLES LIKE '%customer%' - Use IN ACCOUNT to search across all databases (requires privileges)
- Snowflake identifiers are case-insensitive unless double-quoted
- INFORMATION_SCHEMA requires uppercase for filter values
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.
- 16d ago First seen · 85 lines · 36 tokens per session scan A 8f100c2f989c
snowflake-explore is a skill published in the GitHub repository Snowflake-Labs/snowflake-ai-kit (42 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 456 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 2026-10-24.
snowflake-explore compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| snowflake-exploreSnowflake-Labs/snowflake-ai-kit | Skill | 42 | 3d ago | Apache-2.0 | A | 36 | Claude Code |
| wisdom-indexSnowflake-Labs/cocoplus | Skill | 728 | 2d ago | MIT | A | 21 | Claude Code, Codex |
| snowflake-to-bigquery-converterlooker-open-source/looker-skills | Skill | 46 | 3d ago | Apache-2.0 | A | 83 | Claude Code |
| ecommerce-data-warehousefinsilabs/awesome-ecommerce-skills | Skill | 63 | 17d ago | MIT | A | 35 | Claude Code, Codex |
| snowflake-syntheticdynatrace-oss/dynatrace-snowflake-observability-agent | Skill | 10 | 3d ago | MIT | A | 19 | OpenCode |
| snowflake-mcpchristianclaudio/mcp-server-snowflake | Skill | 1 | yesterday | Apache-2.0 | A | 45 | Claude Code, Codex |
| data-engineerbuiphucminhtam/forgewright | Skill | 49 | 2d ago | none | A | 85 | Claude Code |