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 validate-sas-conversiongit 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/validate-sas-conversion)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/validate-sas-conversion"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/validate-sas-conversion/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/validate-sas-conversion"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/validate-sas-conversion.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 | $0.00080 | $0.04916 |
| Opus 5 | $0.00040 | $0.02458 |
| Sonnet 5 | $0.00016 | $0.00983 |
| Haiku 4.5 | $0.00008 | $0.00492 |
Grade A, and why
validate-sas-conversion 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 — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate SAS to Snowflake Conversion
Dual-execution comparison framework: LLM traces SAS logic to produce expected baselines, then executes converted SQL on Snowflake and compares.
Execution Model
| Component | Engine | Snowflake? |
|---|---|---|
| Synthetic data generation | LLM + SQL | Yes (temp tables) |
| SAS logic trace (expected baseline) | LLM | No |
| Converted SQL execution | Snowflake | Yes |
| Output comparison | SQL MINUS/EXCEPT | Yes |
| Artifact persistence | CSV + SQL files to disk | No |
Snowflake is used for execution with explicit credit confirmation per Snowflake Interaction Policy.
When to Load
[convert-sas-to-snowflake] Step 8: After user opts to validate conversion, or when user explicitly requests validation of existing converted code.
Arguments
$CONVERTED_CODE- Path to converted.sqlfile or SQL code to validate$ORIGINAL_SAS- Path to original SAS code (REQUIRED for baseline generation)
Rules
- Never modify the converted code - Create test wrapper/harness separately
- Original SAS code is REQUIRED - Cannot generate baseline without it
- Schema inference - Derive from SQL CREATE statements, SELECT columns, or original SAS
- Persist all test artifacts - Save synthetic data, expected baselines, actual results, and validation reports to disk subfolders (see Artifact Persistence below)
- Load reference files - Read
references/synthetic-data-rules.mdandreferences/comparison-rules.mdbefore generating data or comparing - Snowflake execution - All SQL execution runs on Snowflake with explicit credit confirmation per Snowflake Interaction Policy.
Artifact Persistence
All test artifacts MUST be persisted to disk in the conversion output directory. This enables reproducibility, audit trails, and inclusion in the conversion report.
Directory Structure
Create the following subfolder structure relative to the conversion output directory (same directory as the generated .sql files):
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 · 553 lines · 80 tokens per session scan A c4ea3accaa9d
validate-sas-conversion 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 80 tokens to every session and 4,916 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
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
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…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
azure-cosmos-db-py
Build Azure Cosmos DB NoSQL services with Python/FastAPI following production-grade patterns. Use when implementing database client setup with dual auth (DefaultAzureCredential + emulator), service layer classes with CRUD operations, partition key strategies, parameterized queries, or TDD patterns for Cosmos. Triggers…
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
Drizzle ORM Testing
Testing patterns for Drizzle ORM covering migration testing, query builder testing, transaction testing, and database integration testing with PostgreSQL, SQLite, and MySQL.