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/snowflake-labs/snowflake-ai-kit/cortex-setupnpx skills add Snowflake-Labs/snowflake-ai-kit --skill cortex-setupgit 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/cortex-setup)<a href="https://agentmods.dev/skills/snowflake-labs/snowflake-ai-kit/cortex-setup"><img src="https://agentmods.dev/badge/skills/snowflake-labs/snowflake-ai-kit/cortex-setup.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.01148 |
| Opus 5 | $0.00032 | $0.00574 |
| Sonnet 5 | $0.00013 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade D, and why
cortex-setup scanned grade D with 3 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://docs.snowflake.com/en/user-guide/cortex-code/cortex-code-cli | bash Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json 2>/dev/null | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://docs.snowflake.com/en/user-guide/cortex-code/cortex-code-cli | bash How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Code Setup
Install Snowflake CLI (snow) and Cortex Code CLI (cortex) using the appropriate installer for the current OS.
Prerequisite — ALWAYS run this FIRST, unconditionally
Before doing ANYTHING else in this skill, you MUST run this check. This is not optional. Do not skip it even if the CLIs are already installed.
cat ~/.claude/settings.json 2>/dev/null | python3 -c "
import sys, json
try:
settings = json.load(sys.stdin)
servers = settings.get('mcpServers', {})
for name, cfg in servers.items():
cmd = cfg.get('command', '') + ' ' + ' '.join(cfg.get('args', []))
if 'snowflake' in name.lower() or 'snowflake' in cmd.lower():
print(f'CONFLICT: {name}')
sys.exit(1)
except: pass
print('OK: No Snowflake MCP server found')
"
If exit code is 1 (conflict found), STOP IMMEDIATELY and tell the user:
⚠️ Snowflake MCP Server detected. The Cortex Code plugin replaces the Snowflake MCP server with more capabilities (security envelopes, session management, multi-turn). Please disable the MCP server before continuing:
- Open
~/.claude/settings.json- Remove the Snowflake MCP server entry from
"mcpServers"- Restart Claude Code
Then re-run this setup.
Do NOT proceed. Do NOT check CLI versions. Do NOT install anything. STOP HERE.
When to use
- Cortex Code CLI is not found on PATH
- User asks to set up or install Cortex Code
- Routing failed because
cortexbinary is missing
Steps
1. Detect OS and check current state
import platform
print(platform.system()) # "Windows", "Darwin", or "Linux"
Windows (Command Prompt or PowerShell):
where cortex 2>nul && cortex --version || echo "cortex not installed"
where snow 2>nul && snow --version || echo "snow not installed"
macOS / Linux:
which cortex 2>/dev/null && cortex --version || echo "cortex not installed"
which snow 2>/dev/null && snow --version || echo "snow not installed"
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.
- 4d ago First seen · 151 lines · 63 tokens per session scan D 69f6c553d5da
cortex-setup is a skill published in the GitHub repository Snowflake-Labs/snowflake-ai-kit (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,148 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
snowflake-integration-testing
Integration testing workflow for mcp-snowflake-server. Use when verifying MCP tool connectivity, exploring Snowflake schemas, discovering tables with specific column types (VARIANT, OBJECT, ARRAY, nested JSON), and sampling data. Trigger phrases: "integration test", "test snowflake connection", "explore snowflake"…
sql-sentinel
Audit SQL for the cost & performance anti-patterns that burn warehouse credits. Catches SELECT , full-table scans, non-sargable predicates, Cartesian joins, NULL-trap NOT IN, and 17 more rules. Scores warehouse health 0-100 and outputs a prioritized cost-reduction plan for BigQuery, Snowflake, Redshift, and Postgres.
snowflake-expert
Expert-level Snowflake data warehouse platform, virtual warehouses, data sharing, streams, tasks, and SQL optimization.
snowflake-mcp
Enterprise Agent Skill for orchestrating Snowflake Data Cloud, Warehouses, Zero-Copy Clones, Tasks, Streams, SPCS, Governance, and Cortex AI with mcp-server-snowflake.
sql-revision
Verify that a SQL query's actual output faithfully answers the natural-language question.
sql-writing
Construct a SQL query that correctly answers a natural-language question grounded in the actual database.