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 agentmods add skills/linuxfoundation/lfx-self-serve/snowflakenpx skills add linuxfoundation/lfx-self-serve --skill snowflakegit clone --depth 1 https://github.com/linuxfoundation/lfx-self-serveWhat 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 | $0.00066 | $0.00609 |
| Opus 5 | $0.00033 | $0.00304 |
| Sonnet 5 | $0.00013 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
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 3d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self Serve Snowflake Skill
You are writing or modifying SQL that runs against Snowflake through Self Serve's singleton connection pool. SQL bind alignment is the most common Critical bug in this area.
When to use
- Adding a new analytics endpoint (Snowflake-backed) under
apps/lfx-one/src/server/. - Modifying a query that touches
snowflake.service.tsdirectly. - Adding a new SQL file or modifying an existing one that uses
?placeholders. - Investigating dropped rows, wrong counts, or "snowflake disconnected" errors.
Workflow
- Re-read
docs/architecture/backend/snowflake-integration.md(the reference linked below). It documents the singleton pool, query deduplication, warehouse selection, and result-set handling. - Bind discipline — every
?placeholder in the SQL must have a corresponding value in the binds array, in the correct order. Bind mismatch is always Critical (the reviewer will flag it). Walk left-to-right through the SQL and count?; the binds array length must equal that count. - Do not bypass the singleton pool.
snowflake.service.tsis a protected file. New consumers go through it; new query methods extend it under code-owner review. - Parameterize, never interpolate. No string concatenation of user input into SQL.
- For project- or persona-scoped queries, filter by the right Snowflake column up front; do not over-fetch and filter in JS.
- Log via the
loggerservice (notserverLogger). Uselogger.debugfor query tracing,logger.warningfor empty results when a result was expected. - For known-false-positive patterns (e.g., empty result sets that are valid), check
docs/reviews/knowledge-base/data-and-snowflake.md.
Reference
docs/architecture/backend/snowflake-integration.md— the canonical Snowflake architecture doc. Treat this as the source of truth; do not maintain a separate copy under this skill.
Scope boundaries
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.
- 3d ago First seen · 36 lines · 66 tokens per session scan A c7a1111dae51
snowflake is a skill published in the GitHub repository linuxfoundation/lfx-self-serve (11 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 609 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 2026-08-30.
Other skills, from other repositories
prisma-upgrade-v7
Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on "upgrade to prisma 7", "prisma 7 migration", "prisma-client generator", "driver adapter required".
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
sqlitecpp-update-sqlite
How to update the bundled SQLite3 amalgamation (sqlite3/sqlite3.c and sqlite3.h), the Meson wrap, README.md, and CHANGELOG.md. Use when upgrading SQLite, refreshing the vendored amalgamation, or bumping the sqlite3 wrap.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK…
mongodb-natural-language-querying
Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter/query/aggregate data in MongoDB, asks "how do I query...", needs help with…
sql-translate
Translate SQL queries between database dialects (Snowflake, BigQuery, PostgreSQL, MySQL, etc.).