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 d-padmanabhan/agent-engineering-handbook --skill snowflakegit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/snowflake)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/snowflake"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/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/d-padmanabhan/agent-engineering-handbook/snowflake"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/snowflake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.02532 |
| Opus 5 | $0.00028 | $0.01266 |
| Sonnet 5 | $0.00011 | $0.00506 |
| Haiku 4.5 | $0.00006 | $0.00253 |
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 9d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snowflake - Playbook
Companion rule: 482-snowflake.mdc. This skill turns those patterns into end-to-end workflows.
When to invoke
Use when the user is:
- Designing a new Snowflake account, database, or warehouse
- Rolling out or auditing RBAC (roles, grants, object ownership)
- Tuning cost (warehouse sizing, auto-suspend, query optimization, storage)
- Building pipelines with Snowpipe, Streams, Tasks, or Dynamic Tables
- Setting up secure data sharing (Reader Accounts, Snowflake Marketplace, Private Listings)
- Recovering from a bad change (Time Travel, Fail-safe)
- Governing sensitive data (masking, row access policies, tagging)
Golden Rules
- Roles hold privileges; users hold roles. Never grant directly to users.
- Use
USE ROLEat the top of every script. Implicit roles cause access-denied mysteries. - Warehouses suspend aggressively (60s auto-suspend for interactive; higher for streaming).
- Right-size warehouses; scale with multi-cluster, not with XL.
- Time Travel is real; Fail-safe is last-resort. Set retention deliberately per schema.
- Every production role chain has an owner and an audit trail.
Workflow 1 - RBAC Rollout
Design a production-grade role hierarchy and migrate away from ACCOUNTADMIN-as-default.
Steps
- Map your access model to Snowflake's RBAC:
- System roles:
ORGADMIN,ACCOUNTADMIN,SECURITYADMIN,USERADMIN,SYSADMIN,PUBLIC - Custom roles: business- and data-oriented
- System roles:
- Use the standard hierarchy:
- Functional roles (granted to users): e.g.,
ANALYST_SALES,ENGINEER_DATA,ADMIN_FINOPS - Access roles (hold privileges on objects): e.g.,
DB_SALES_READ,DB_SALES_WRITE,WH_LOAD_USE - Functional roles inherit from access roles, not from each other
- Functional roles (granted to users): e.g.,
- Ownership:
- Custom databases / schemas / warehouses are OWNED by a custom role (e.g.,
DB_SALES_OWNER), never byACCOUNTADMIN SYSADMINsits above functional roles; custom-role-owned objects grant managed access through their owner role
- Custom databases / schemas / warehouses are OWNED by a custom role (e.g.,
- USE MANAGED ACCESS schemas for any schema where multiple teams grant access - centralize grant control.
- Separation of duties:
USERADMINmanages users + role grants;SECURITYADMINmanages privilege grants on objects; they do NOT overlap- Application service users are locked to a specific role via
DEFAULT_ROLEand cannot switch
- Audit:
- Snapshot
GRANTSto a governance schema nightly (SNOWFLAKE.ACCOUNT_USAGE.GRANTS_TO_ROLES) - Alert on new grants to
ACCOUNTADMIN/SECURITYADMIN
- Snapshot
- Terraform / dbt:
- Manage roles and grants via
snowflake-terraform-provider(Snowflake Labs) or Permifrost (dbt Labs) - PR-reviewed changes; drift detection
- Manage roles and grants via
- Migrate existing access incrementally; lock down
ACCOUNTADMIN-for-daily-use.
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.
- 9d ago First seen · 263 lines · 55 tokens per session scan A fac9bf43b37a
snowflake is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (17 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 2,532 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 2026-09-03.
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.