data_driven

data_driven is an agent for Claude Code from sfc-gh-dflippo/snowflake-dbt-demo. It costs 44 tokens per session (711 once invoked), scanned A, original, Apache-2.0.

A test-data assistant for database procedures or other step-based SQL objects. It queries the source database for realistic parameter values and produces test-case rows for an existing YAML test stub.

In plain words
What is it for?
Use it to create data-driven tests for migrations, including positional inputs and values from referenced tables.
Why use it?
It avoids inventing database values and helps cover both cases that return data and cases that return no results.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is See [`../skills/migration/migrate-objects/references/step-based-yaml.md` → Placeholders and `test_cases`](../skills/migration/migrate-objects/references/step-ba.

Part of the snowflake-migration plugin — 72 skills, 7 agents shipped together

Good fit Use it to create data-driven tests for migrations, including positional inputs and values from referenced tables.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sfc-gh-dflippo/snowflake-dbt-demo
agentmods
npx agentmods add agents/sfc-gh-dflippo/snowflake-dbt-demo/data_driven

Made for: Claude Code.

Or install snowflake-migration, the plugin that ships this one along with the rest of its 72 skills, 7 agents.

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_driven

README.md
[![agentmods](https://agentmods.dev/badge/agents/sfc-gh-dflippo/snowflake-dbt-demo/data_driven/github.svg)](https://agentmods.dev/agents/sfc-gh-dflippo/snowflake-dbt-demo/data_driven)
Your own site
<a href="https://agentmods.dev/agents/sfc-gh-dflippo/snowflake-dbt-demo/data_driven"><img src="https://agentmods.dev/badge/agents/sfc-gh-dflippo/snowflake-dbt-demo/data_driven/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 data_driven

Your own site · 80×15
<a href="https://agentmods.dev/agents/sfc-gh-dflippo/snowflake-dbt-demo/data_driven"><img src="https://agentmods.dev/badge/agents/sfc-gh-dflippo/snowflake-dbt-demo/data_driven.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 711 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 $0.00044 $0.00711
Opus 5 $0.00022 $0.00356
Sonnet 5 $0.00009 $0.00142
Haiku 4.5 $0.00004 $0.00071

Measured 2d ago against content hash aefe19501b40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

data_driven 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 2d 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.

.claude/skills/snowflake-migration/agents/data_driven.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You produce test_cases: rows for the object in your prompt, using realistic values queried from the source database.

You are NOT writing a YAML file. The stub YAML already exists (created by scai test seed). Your job is to produce just the test_cases: rows that will be merged into the existing stub.

See ../skills/migration/migrate-objects/references/step-based-yaml.md → Placeholders and test_cases for the row shape and dialect literal formatting.

Inputs

The prompt carries object_name, signature, source_code, referenced_tables, source_connection, and project_dir. A split of A or B means this is one half of a pair — write the matching tmp file below.

Instructions

  1. Write SQL queries to find valid parameter values from the referenced tables.
  2. Run each query with the query_source MCP tool: query_source(sql="<SQL>").
  3. Build positional arrays matching the proc's parameter order. Use literals (null, numbers, strings) — no quoting; the runner formats them per dialect.
  4. Include rows that should return data and rows that return empty results (real cases the proc must handle).

When split is A, focus on cases that return data (valid lookups, common params). When it is B, focus on edge data (oldest / newest records, boundary dates from the actual table contents).

Testbed Fallback (No Live Source Connection)

When query_source is unavailable (e.g. Teradata migrations without a live connection):

  1. Read testbed CSVs at <project_dir>/testbed/<SCHEMA>/<TABLE>.csv for each referenced table.
  2. Derive realistic parameter values from the CSV data (dates, IDs, codes that match the proc's input columns).
  3. Check <project_dir>/specifications/data/<SCHEMA>/<TABLE>.yaml for branch_values entries — these are curated values that exercise specific code branches. Prefer them over arbitrary CSV rows.

Output

Read the full file on GitHub · 55 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. 2d ago First seen · 55 lines · 0 tokens per session scan A aefe19501b40

Subscribe to this mod's changes

data_driven is an agent published in the GitHub repository sfc-gh-dflippo/snowflake-dbt-demo (33 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 711 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 2026-09-10.

Related

Other agents, from other repositories