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 skills add sfc-gh-dflippo/snowflake-dbt-demo --skill etl-seedgit clone --depth 1 https://github.com/sfc-gh-dflippo/snowflake-dbt-demoWrote 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/sfc-gh-dflippo/snowflake-dbt-demo/etl-seed)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/etl-seed"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/etl-seed/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.
<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/etl-seed"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/etl-seed.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00053 | $0.02120 |
| Opus 5 | $0.00026 | $0.01060 |
| Sonnet 5 | $0.00011 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
etl-seed 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ETL Seed
Generates the kind: etl test YAML for a single, already-deployed ETL code unit at artifacts/<id>/etl-test/<name>.yml. The YAML declares the pipeline (how to launch the source package and which converted target to run) and a validation.tables list of source→target table pairs to compare.
scai test seed seeds ETL units — you do not hand-author the file. For an ETL unit (kind = 'etl'; SSIS or Informatica natively, any platform once an external_command: section opts in — see Step 2) scai test seed walks the Code Unit Registry, takes the unit's write dependencies (INSERT / UPDATE / MERGE / DELETE), and emits a validation.tables entry per written table — pairing the source table (source.canonicalName) with its Snowflake target (target.canonicalName). It leaves index_columns blank for you to fill. Your job is to run the seeder, fill in the join keys, handle any skipped units, and confirm with the user — not to invent table pairs.
Step 0: Resolve Unit
Read the registry entry (the executor passes object_id; if entered by name, locate via migration_status(mode="my_objects_summary")):
| Field | Used as |
|---|---|
id |
{ETL_ID} for the --where filter and the artifacts/<id>/etl-test/ path |
source.platform |
source kind (ssis, informatica, …) |
files.source.path |
source definition file (.dtsx, .xml, …); its stem is the YAML file name |
The etlSeed task has a taskCompleted precondition on deploy, so the executor only dispatches this skill once the unit is deployed — you do not need to re-check deployment here.
Step 1: Run scai test seed
scai test seed --where "id = '{ETL_ID}'"
Add --append when a YAML already exists for the unit — it re-emits the table pairs from the current CUR while preserving your edited index_columns / test_cases (matched per source→target pair):
scai test seed --where "id = '{ETL_ID}'" --append
Platform is auto-detected per unit from the registry — no --platform flag. On success the file is written to artifacts/{ETL_ID}/etl-test/<name>.yml with the execution block and table pairs filled from the CUR. When an external_command: section is present, the side it names is emitted as {type: external_command, wait_seconds: <n>} — two keys and nothing else, since the command itself lives only in test_config.yaml — and the other side keeps its native block. Tune wait_seconds per unit if one package runs longer than the shared default.
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.
- 2d ago First seen · 127 lines · 53 tokens per session scan A 8eee8ff49aef
etl-seed is a skill published in the GitHub repository sfc-gh-dflippo/snowflake-dbt-demo (33 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,120 once invoked, about $0.0003 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.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
shaft-automated-test-authoring
Use when implementing or repairing executable SHAFT Java tests for web, mobile, API, database, CLI, TestNG, JUnit, or Cucumber behavior.
shaft-database-testing
Use when implementing or repairing SHAFT.DB checks for persisted state, queries, rows, transactions, cleanup, or database-backed integration behavior.
multi-agent-e2e-validation
Multi-agent parallel E2E validation for database refactors. TRIGGERS - E2E validation, schema migration testing, database refactor validation.
schema-e2e-validation
Earthly E2E validation for YAML schema contracts. TRIGGERS - schema validation, YAML schema, schema contracts, regenerate types.
mock-and-fixture-generator
Generates realistic, edge-case-rich mock fixtures and synthetic API payloads without leaking real PII.