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/convert-sas-to-snowflakeWrote 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/convert-sas-to-snowflake)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/convert-sas-to-snowflake"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/convert-sas-to-snowflake/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/convert-sas-to-snowflake"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/convert-sas-to-snowflake.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 | $0.00099 | $0.10939 |
| Opus 5 | $0.00049 | $0.05470 |
| Sonnet 5 | $0.00020 | $0.02188 |
| Haiku 4.5 | $0.00010 | $0.01094 |
Grade A, and why
convert-sas-to-snowflake 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 — 761 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convert SAS to Snowflake
© Snowflake Inc. This skill and its contents are the proprietary intellectual property of Snowflake Inc.
Expert SAS to Snowflake migration - ALWAYS outputs .sql by default, with PySpark/SCOS as last resort.
Output: .sql by default (Tier 1 SQL + Tier 2 Stored Procedures). PySpark/SCOS notebook = LAST RESORT (HASH objects, CALL EXECUTE, statistical procs only). See SQL-First Classification below for full tier tables.
Snowflake Interaction Policy: ALL Snowflake operations (object creation, compilation, testing) require explicit user confirmation. See workflows/steps-8-10-post-conversion.md for confirmation patterns and testing mode selection.
User Consent Propagation: When a user confirms a high-level decision (validation scope, compilation approval), downstream sub-decisions that are direct consequences auto-resolve without re-prompting. See "Consent Propagation Rules" section below.
Validation Prompt Policy (EXPLICIT — No Auto-Propagation)
Each validation phase requires its own explicit user confirmation. No phase auto-proceeds based on a prior selection. Snowflake operations ALWAYS show credit impact before executing.
| Phase | Prompt | Credits | Can Skip? |
|---|---|---|---|
| Phase 1: Synthetic Data | Always runs (no prompt needed) | Zero | No |
| Phase 2: LLM Trace | "Run LLM trace?" | Zero | Yes |
| Phase 3: Snowflake Compilation | "Compile on Snowflake?" (with credit estimate) | Minimal | Yes |
| Phase 4: Snowflake Execution (Tier 2/3) | "Execute on Snowflake?" (with credit estimate) | Moderate | Yes |
Hard Artifact Gates: Each phase produces artifacts on disk. The NEXT phase CANNOT begin unless the prior phase's gate passes (artifacts verified to exist). State file updates without corresponding disk artifacts are INVALID.
| Phase | Required Artifacts |
|---|---|
| Phase 1 | source_table_ddl.sql + synthetic_data.sql |
| Phase 2 | tests/<file>/expected/expected_<table>.csv for each traced file |
| Phase 3 | compilation_results.json with per-file pass/fail |
| Phase 4 | snowflake_execution_results.json |
What ships with it
35 files 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.
- references/auto-validation.md 11 KB
- references/batch-mode.md 9.6 KB
- references/checkpoint-logging.md 5.3 KB
- references/classification-logic.md 5.9 KB
- references/common-patterns.md 16 KB
- references/comparison-rules.md 6.8 KB
- references/consolidation-patterns.md 9.3 KB
- references/conversion-rules.md 18 KB
- references/data-steps.md 13 KB
- references/e2e-orchestration-test.md 8.0 KB
- references/function-mappings.md 14 KB
- references/large-file-rules.md 3.8 KB
- references/macros.md 14 KB
- references/mermaid-diagrams.md 6.3 KB
- references/multi-block-orchestration.md 9.4 KB
- references/proc-sql.md 6.6 KB
- references/proc-steps.md 19 KB
- references/pyspark-fallback.md 5.7 KB
- references/python-datascience.md 6.7 KB
- references/schema-inference.md 6.6 KB
- references/snowflake-compile.md 6.3 KB
- references/snowflake-execution.md 10 KB
- references/state-tracker-schema.md 7.9 KB
- references/synthetic-data-rules.md 11 KB
- references/validation-execution.md 9.2 KB
- references/vendor-function-mappings.md 4.3 KB
- references/vendor-passthrough.md 2.6 KB
- templates/consolidation-report.md 6.9 KB
- templates/conversion-report.md 28 KB
- templates/output-mixed.md 8.9 KB
- templates/output-sql.md 3.2 KB
- validate-sas-conversion/SKILL.md 21 KB
- workflows/steps-7-validation.md 8.0 KB
- workflows/steps-8-10-post-conversion.md 20 KB
- workflows/validation-pipeline.md 13 KB
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 · 761 lines · 99 tokens per session scan A 9e10e26612d6
convert-sas-to-snowflake 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 99 tokens to every session and 10,939 once invoked, about $0.0005 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.