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.
git clone --depth 1 https://github.com/sfc-gh-dflippo/snowflake-dbt-demonpx agentmods add skills/sfc-gh-dflippo/snowflake-dbt-demo/proc-test-genWrote 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/proc-test-gen)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/proc-test-gen"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/proc-test-gen/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/proc-test-gen"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/proc-test-gen.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 | $0.00083 | $0.03563 |
| Opus 5 | $0.00042 | $0.01782 |
| Sonnet 5 | $0.00017 | $0.00713 |
| Haiku 4.5 | $0.00008 | $0.00356 |
Grade A, and why
proc-test-gen 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proc Test Generator (scripting flavor)
Generate and run a functional-equivalence check for a single converted mapping procedure — an
Informatica mapping converted to a standalone Snowflake Scripting stored procedure — from the original
data-flow logic in the source mapping. The expected target-table contents are computed from the source
mapping applied to the seeded input, NOT from the converted SQL under repair, so the assertions are an
independent oracle. All generated artifacts are stored in <UNIT>/stabilization/tests/proc/<proc_name>/.
Scope. This is the data-flow counterpart to orchestration-test-gen: orchestration-test-gen tests control-flow elements of a task graph; proc-test-gen tests the output table of one mapping proc. It is the scripting-flavor analog of dbt-test-gen. In dbt mode a mapping becomes a model (tested by dbt-test-gen); in scripting mode a mapping becomes its own
kind=etlstored procedure, tested here.
Autonomous mode: When spawned as a team agent, skip all interactive stopping points, make reasonable defaults, and document assumptions in the completion report. When done,
send_messagetomainwith your results, and respond to anyshutdown_requestwithtype: "shutdown_response",approve: true.
Where this sits in the fix loop
block-locate ── the defective block + its source transform node (scripts/stabilization_tools.py block-locate, marker-scoped)
proc-fixer ── [agentic] author the fixed block SQL from the source node (sibling sub-skill)
block-replace ── splice the fix back, marker-integrity checked (scripts/stabilization_tools.py block-replace)
deploy-and-call ─ deploy the one proc into the test schema + smoke-CALL it (scai code deploy-and-call)
proc-test-gen ── [THIS SKILL] derive the source-of-truth expected target contents + batched assertions
grade ── run the assertions against the populated target; PASS/FAIL feeds the fixer loop
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 230 lines · 83 tokens per session scan A 10ccb321221c
proc-test-gen 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 83 tokens to every session and 3,563 once invoked, about $0.0004 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
adding-dbt-unit-test
Creates unit test YAML definitions that mock upstream model inputs and validate expected outputs. Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt.
phpunit-migration-test-generation
Use this skill when the user asks to generate, write, or create migration tests for a Shopware 6 migration class — phrases like "generate migration tests", "write a migration test", "create migration test", "test this migration", "test Migration1234Foo". Analyzes the source migration's SQL operations to pick an…
testing-paperclip
Paperclip-Testing-Strategie — Vitest, Plugin-Test-Harness aus @paperclipai/plugin-sdk/testing, echte Postgres-Integration-Tests, Cross-Tenant-Isolation. Verwenden Sie dies beim Schreiben oder Reviewen von Paperclip-Tests.
seed
Database seeding, test fixtures, factory patterns, fake data generation. Idempotent seed scripts.
smoke-test-database
Quick Reference - Load this first for fast context (3KB).
pytest-databases
Auto-activate for pytestdatabases, Docker DB fixtures, PostgreSQL/pgvector/ParadeDB, MySQL/MariaDB, Oracle/SQL Server, CockroachDB/YugabyteDB, MongoDB, Redis/Valkey, Elasticsearch, BigQuery/Spanner, Azurite, MinIO, or RustFS tests. Not for mocked databases.