What is snowflake-ai-kit AGENTS.md?

A set of repository rules for snowflake-ai-kit, a developer toolkit for building applications on Snowflake with AI coding agents. Snowflake is a cloud data platform, and the project includes tools that route suitable requests to Snowflake's Cortex Code command-line tool.

Use it when working on the Cortex Code plugin, prompt routing, setup and installers, credential handling, skills, tests, or documentation.

It explains the repository structure, routing behavior, installation scripts, and checks needed when changing the toolkit.

snowflake-ai-kit AGENTS.md — Instructions file for Codex and OpenCode by Snowflake-Labs: A set of repository rules for snowflake-ai-kit, a d

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.

agentmods

npx agentmods add instructions/snowflake-labs/snowflake-ai-kit/agents-md

Clone the repo

git clone --depth 1 https://github.com/Snowflake-Labs/snowflake-ai-kit

Made for: Codex, OpenCode.

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/instructions/snowflake-labs/snowflake-ai-kit/agents-md.svg)](https://agentmods.dev/instructions/snowflake-labs/snowflake-ai-kit/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/snowflake-labs/snowflake-ai-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/snowflake-labs/snowflake-ai-kit/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 929 This file is loaded in full into every session.

When invoked 929 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00929	$0.00929
Opus 5	$0.00464	$0.00464
Sonnet 5	$0.00186	$0.00186
Haiku 4.5	$0.00093	$0.00093

Measured 5d ago against content hash c580bd8c95a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

snowflake-ai-kit AGENTS.md 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 5d 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.

AGENTS.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines — snowflake-ai-kit

What This Repo Is

Developer tools for building on Snowflake with AI coding agents. Includes a Claude Code plugin (auto-routes Snowflake prompts to Cortex Code) and installers (shell + PowerShell + npx).

Architecture

plugins/
  cortex-code/                                ← Claude Code plugin (v3.0.1)
    .claude-plugin/plugin.json                ← plugin manifest
    hooks/hooks.json                          ← UserPromptSubmit hook (prompt_filter.py)
    scripts/router/
      prompt_filter.py                        ← keyword detection, fires additionalContext
      discover_cortex.py                      ← finds Cortex CLI + discovers skills
      execute_cortex.py                       ← spawns cortex CLI, credential blocking
      route_request.py                        ← indicator scoring + skill trigger matching
    skills/
      cortex-router/                          ← auto-routing skill
      cortex-run/                             ← explicit invocation ($cortex-run)
      cortex-setup/                           ← CLI install + connection setup
install.sh / install.ps1 / bin/install.mjs    ← one-command installers
tests/
  run-tests.sh                                ← bash test runner (Mac/Linux)
  run-tests.ps1                               ← PowerShell test runner (Windows)
  validate-install.ps1                        ← install validation
.github/workflows/
  test.yml                                    ← CI: runs tests on macOS + Windows

Critical Rules

Never commit credentials. Use environment variables or Snowflake built-in auth.
License: Root LICENSE is Apache 2.0.
Branch protection: PRs required on main.
README uses HTTPS clone URLs (not SSH) — keep it that way for external users.

Plugin Scripts

prompt_filter.py — reads message field from stdin JSON. Returns additionalContext for Snowflake-related prompts, {} otherwise.
discover_cortex.py — finds Cortex CLI binary and parses skill output. Has Windows/macOS/Linux path handling.
execute_cortex.py — spawns cortex CLI subprocess. Key behaviors: credential path blocking (CREDENTIAL_PATTERNS), break-on-result, process.terminate() cleanup. The stdin=DEVNULL fix prevents the subprocess from stealing terminal input — do not remove it.
route_request.py — scores prompts via keyword indicators and skill trigger matching. Known issue: single-word trigger matching at line 88 can produce false positives.

Read the full file on GitHub · 78 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.

5d ago First seen · 78 lines · 929 tokens per session scan A c580bd8c95a2

Subscribe to this mod's changes

snowflake-ai-kit AGENTS.md is an instructions file published in the GitHub repository Snowflake-Labs/snowflake-ai-kit (37 stars, last pushed 22d ago), licensed Apache-2.0. It adds 929 tokens to every session, about $0.0046 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.

Building agents Data and AI claude-code cortex-code developer-tools snowflake snowflake-ai snowflake-cli

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

Azure/GPT-RAG · 207 tokens

snowflake-ai-kit AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agent Guidelines — snowflake-ai-kit

What This Repo Is

Architecture

Critical Rules

Plugin Scripts

What this file has done since we first saw it

Other instructions, from other repositories

GPT-RAG release.instructions.md

apex-accelerator vendor-prompting.instructions.md

ken CLAUDE.md

rag-code-mcp copilot-instructions.md

ZipAI CLAUDE.md

TreeSkill CLAUDE.md