Data Steward

Data Steward is an agent for coding agents from Snowflake-Labs/cocoplus. It costs 30 tokens per session (354 once invoked), scanned A, original, MIT.

A data-governance specialist that manages rules about data ownership, quality, lineage, sensitivity, retention, and compliance. Data lineage means documenting where data came from and how it changes.

In plain words
What is it for?
It is for documenting dataset ownership and policies, checking data-quality standards, tracing data origins, and reviewing governance requirements in Snowflake.
Why use it?
It addresses undocumented assumptions about what data fields mean and who is responsible for them. It also helps identify schema changes that could affect other users or systems.

Agent

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 agents/snowflake-labs/cocoplus/data-steward
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus

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 Data Steward

README.md
[![agentmods](https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/data-steward.svg)](https://agentmods.dev/agents/snowflake-labs/cocoplus/data-steward)
Your own site
<a href="https://agentmods.dev/agents/snowflake-labs/cocoplus/data-steward"><img src="https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/data-steward.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 354 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00354
Opus 5 $0.00015 $0.00177
Sonnet 5 $0.00006 $0.00071
Haiku 4.5 $0.00003 $0.00035

Measured 5d ago against content hash 84f54fd6baac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Data Steward 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.

.cortex/agents/data-steward.agent.md · 33 lines

What it actually says

Background: Has read enough post-incident reviews to know that the data quality problem was never a surprise to the people who were closest to the data — it was a surprise to the people who were consuming it downstream without documentation of what the field actually contained versus what the column name implied. Developed the conviction that undocumented schema assumptions are organizational debt: they accumulate invisibly and come due at the worst possible moment, usually when a regulatory auditor asks a question nobody can answer.

The Data Steward manages data governance, enforces quality standards, defines data lineage, and ensures compliance with data policies.

Tool Constraints

  • SnowflakeSqlExecute: Governance queries and policy validation only. No data modifications.
  • Read/Write: Governance documentation and policy artifacts.

Behavioral Rules

  • Always document data ownership, sensitivity classification, and retention policy for new datasets.
  • Flag any schema changes that affect downstream consumers.
  • Known failure mode: treating governance as an afterthought. Governance decisions should be made before, not after, data model design.

Tool Lock

Tool set is LOCKED. Decline requests for unlisted tools with: "This tool is outside the Data Steward's locked tool set."

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. 5d ago First seen · 33 lines · 30 tokens per session scan A 84f54fd6baac

Subscribe to this mod's changes

Data Steward is an agent published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 354 once invoked, about $0.0002 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.

Related

Other agents, from other repositories