snowflake-dcm

snowflake-dcm is a skill for Claude Code from Snowflake-Labs/snowflake-ai-kit. It costs 45 tokens per session (650 once invoked), scanned A, original, Apache-2.0.

A Snowflake infrastructure-as-code skill for defining databases, schemas, tables, roles, and permissions in YAML files. Infrastructure as code means managing system configuration through versioned files instead of only manual commands.

In plain words
What is it for?
Use it to work with manifest.yml files, DEFINE blocks, deployed DCM or dbt projects, and Snowflake objects managed as code.
Why use it?
It gives database changes a structured, reviewable definition and helps inspect or deploy Snowflake objects managed by DCM projects.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the snowflake plugin — 7 skills shipped together

Good fit Use it to work with manifest.yml files, DEFINE blocks, deployed DCM or dbt projects, and Snowflake objects managed as code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/snowflake-labs/snowflake-ai-kit/snowflake-dcm
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 Snowflake-Labs/snowflake-ai-kit --skill snowflake-dcm
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/snowflake-ai-kit

Made for: Claude Code.

Or install snowflake, the plugin that ships this one along with the rest of its 7 skills.

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.

agentmods badge for snowflake-dcm

README.md
[![agentmods](https://agentmods.dev/badge/skills/snowflake-labs/snowflake-ai-kit/snowflake-dcm/github.svg)](https://agentmods.dev/skills/snowflake-labs/snowflake-ai-kit/snowflake-dcm)
Your own site
<a href="https://agentmods.dev/skills/snowflake-labs/snowflake-ai-kit/snowflake-dcm"><img src="https://agentmods.dev/badge/skills/snowflake-labs/snowflake-ai-kit/snowflake-dcm/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.

agentmods 80×15 button for snowflake-dcm

Your own site · 80×15
<a href="https://agentmods.dev/skills/snowflake-labs/snowflake-ai-kit/snowflake-dcm"><img src="https://agentmods.dev/badge/skills/snowflake-labs/snowflake-ai-kit/snowflake-dcm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 650 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00650
Opus 5.5 $0.00018 $0.00260
Sonnet 5.5 $0.00009 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 16d ago against content hash be698ba4db41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

snowflake-dcm 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.

plugins/snowflake-mcp-devin/skills/snowflake-dcm/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Snowflake DCM (Database Change Management)

DCM lets you manage Snowflake infrastructure as code — databases, schemas, tables, roles, and grants defined declaratively in YAML manifests and deployed through the Snowflake CLI or SQL.

When to use

  • User asks about infrastructure-as-code for Snowflake
  • User mentions DCM projects, manifest.yml, or DEFINE blocks
  • User wants to deploy, inspect, or manage database objects as code
  • User asks about the three-tier role pattern

Discovery

List deployed DCM/dbt projects:

SHOW DBT PROJECTS IN ACCOUNT;

Describe a project:

DESCRIBE DBT PROJECT my_db.my_schema.my_project;

Concepts

Manifest structure

DCM projects use manifest.yml with DEFINE blocks:

# manifest.yml
- DEFINE DATABASE analytics_db:
    comment: "Analytics database managed by DCM"

- DEFINE SCHEMA analytics_db.reporting:
    comment: "Reporting schema"

- DEFINE TABLE analytics_db.reporting.daily_metrics:
    columns:
      - name: METRIC_DATE
        type: DATE
        not_null: true
      - name: METRIC_NAME
        type: VARCHAR(256)
      - name: METRIC_VALUE
        type: NUMBER(18,4)
    comment: "Daily business metrics"

Three-tier role pattern

DCM automatically creates three roles per project:

  • <project>_ADMIN — full DDL on project objects
  • <project>_READWRITE — DML (INSERT, UPDATE, DELETE) on project tables
  • <project>_READONLY — SELECT on project tables and views

CLI commands

# Deploy a DCM project
snow dcm deploy --manifest manifest.yml

# Execute a deployed project
snow dcm execute my_db.my_schema.my_project

# List deployed projects
snow dcm list

SQL commands

-- Execute a deployed project
EXECUTE DBT PROJECT my_db.my_schema.my_project;

-- Alter a project
ALTER DBT PROJECT my_db.my_schema.my_project SET COMMENT = 'Updated';

-- Drop a project
DROP DBT PROJECT my_db.my_schema.my_project;

Drift detection

After deployment, compare the manifest against live state:

  1. DESCRIBE DBT PROJECT <name> — see what was deployed
  2. SHOW TABLES/SCHEMAS/DATABASES — see current state
  3. Re-deploy to reconcile drift

Read the full file on GitHub · 104 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.

  1. 16d ago First seen · 104 lines · 45 tokens per session scan A be698ba4db41

Subscribe to this mod's changes

snowflake-dcm 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 45 tokens to every session and 650 once invoked, about $0.0002 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.

Related

snowflake-dcm compared with skills from other repositories

snowflake-dcm next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
snowflake-dcmSnowflake-Labs/snowflake-ai-kitSkill423d agoApache-2.0A45Claude Code
wisdom-indexSnowflake-Labs/cocoplusSkill7282d agoMITA21Claude Code, Codex
snowflake-to-bigquery-converterlooker-open-source/looker-skillsSkill463d agoApache-2.0A83Claude Code
ecommerce-data-warehousefinsilabs/awesome-ecommerce-skillsSkill6317d agoMITA35Claude Code, Codex
snowflake-syntheticdynatrace-oss/dynatrace-snowflake-observability-agentSkill103d agoMITA19OpenCode
snowflake-mcpchristianclaudio/mcp-server-snowflakeSkill1yesterdayApache-2.0A45Claude Code, Codex
data-engineerbuiphucminhtam/forgewrightSkill492d agononeA85Claude Code