fsnow
Made by JeffRun fsnow/franken-snowflake CLI, MCP, write refusals, FSNOW errors, and Rust APIs. Use when querying Snowflake live/offline, integrating franken_snowflake crates, or working in the repo.
From Jeffrey's Skills.md: professionally crafted skills for any AI agent, installed and kept in sync by the jsm CLI. Subscription only, $20/month.
Works With
Quality and Utility come from canonical skill metadata. Community ratings appear separately as stars when subscriber reviews exist.
Subscribe to download
Public previews are available, but downloads, CLI sync, and premium content require an active subscription.
Sign In to Subscribe- Full skill content with deterministic versioning
- CLI sync + local search index
- Access to Jeffrey’s premium library
Save to your account
Saved skills live in your cloud list. Run jsm sync on each machine to pull them locally.
What's New with this Skill
1Updates, enhancements, and release notes for this skill.
fsnow: a Rust-first Snowflake connector for agents
fsnow (franken-snowflake) gives coding agents a structured CLI, an MCP surface, and a Rust library for Snowflake's SQL API. Every command returns a typed JSON envelope that carries its own provenance, so ok:true is never mistaken for proof. Live access is opt-in twice: a compiled feature flag plus runtime credentials, with data_source=live as the receipt that real Snowflake was touched.
- Structured surfaces first: onboard, capabilities, agent-handbook, and per-command JSON/toon envelopes, so you never scrape human help.
- data_source and outcome_kind are the proof fields; a live task is never proven by ok:true alone.
- Live is opt-in twice: compile with --features live and supply runtime profile handles; missing credentials become typed refusals, not silent passes.
- The query write ladder enforces WRITE_ENABLED, dry-run/confirm tokens, and explicit DDL policy.
- Downstream Rust integration through the SnowflakeDataLakeAdapter boundary, with no Tokio/reqwest/hyper in production graphs.
- Install in one line (curl or PowerShell) or from source with cargo, then verify with fsnow onboard --json.
Snowflake from an agent usually means a Python driver, a pile of credentials in a config file, and output you have to trust on faith. fsnow is built the other way around: a clean-room Rust connector whose agent-facing contract is the product.
Start with fsnow onboard --json and fsnow capabilities --json; the binary reports its commands, feature flags, exit codes, and error registry instead of making you scrape --help. Read queries, catalog scans, lineage graphs, and write mutations all return the same versioned envelope, with outcome_kind and data_source as the fields that actually