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 RelationalAI/rai-agent-skills --skill rai-deploymentgit clone --depth 1 https://github.com/RelationalAI/rai-agent-skillsWrote 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/relationalai/rai-agent-skills/rai-deployment)<a href="https://agentmods.dev/skills/relationalai/rai-agent-skills/rai-deployment"><img src="https://agentmods.dev/badge/skills/relationalai/rai-agent-skills/rai-deployment/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/relationalai/rai-agent-skills/rai-deployment"><img src="https://agentmods.dev/badge/skills/relationalai/rai-agent-skills/rai-deployment.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 | $0.00123 | $0.03231 |
| Opus 5 | $0.00062 | $0.01615 |
| Sonnet 5 | $0.00025 | $0.00646 |
| Haiku 4.5 | $0.00012 | $0.00323 |
Grade A, and why
rai-deployment 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 11d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RelationalAI Deployment (Path to Prod)
Covers the path from a built RelationalAI model to production: the rai models CLI (schema deployment + lifecycle) and Snowflake CoWork (Cortex) agents. Built on the relationalai package (PyRel).
Early access. Deploy mode and semantic model management — the
rai modelsdeploy + branch/collaborate/merge/teardown lifecycle — are early-access features (documented in the RAI docs' early-access section); the API, messages, and defaults may still change. Op-log recording (the basis forbranch/pull/merge) is off by default today, expected to default on soon. Verified against relationalai 1.20.1; see Prerequisites to turn it on. (The Cortex-agent path carries its own GA/PREVIEW markers — see references/cortex-agents.md.)
Summary
What: Everything between a built model and production, by either of two paths. You've built and validated a model; this skill ships it. Schema deployment — deploy into a Snowflake schema and manage its lifecycle: track every change in the op log, fork experiments into branches, collaborate through a shared model, promote vetted changes back with merge, and tear models down safely. Cortex agent — package the model as a Snowflake CoWork agent users query in natural language.
When to use:
- Deploying a model to a Snowflake schema (
rai models deploy) and understanding what the op log records - Branching a deployed model for isolated experiments (
rai models branch) - Collaborating with other developers on one model (shared model,
rai models pull) - Promoting a branch back to its parent (
rai models merge) or removing a model (rai models teardown) - Deploying a model as a Snowflake CoWork (Cortex) agent
- Choosing a path to prod (schema deployment vs. Cortex agent)
When NOT to use:
- First-time install,
rai connect, orraiconfig.yamlauth/engine tuning — seerai-setup - Building or evolving the model itself (concepts, rules, queries) — see
rai-ontology,rai-pyrel - Diagnosing engine performance or failed transactions — see
rai-health
What ships with it
13 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.
- examples/__init__.py 0 B runs code
- examples/debug.py 9.1 KB runs code
- examples/deploy.py 6.3 KB runs code
- examples/model/__init__.py 0 B runs code
- examples/model/computed.py 1.4 KB runs code
- examples/model/core.py 1.3 KB runs code
- examples/model/queries.py 684 B runs code
- examples/README.md 1.3 KB
- references/branching.md 3.8 KB
- references/collaboration.md 3.4 KB
- references/cortex-agents.md 41 KB
- references/deploy-and-oplog.md 6.8 KB
- references/merge-and-teardown.md 3.9 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.
- 11d ago First seen · 157 lines · 123 tokens per session scan A 8bb4ce0c1d03
rai-deployment is a skill published in the GitHub repository RelationalAI/rai-agent-skills (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 3,231 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
google-cloud-storage-fuse
Mounts Cloud Storage buckets as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when interacting with gcsfuse: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size file, stat, and list caches, tune…
cloud-databases-onboarding
Guides users through discovering their database requirements, recommends a Google Cloud database based on a recommendation matrix, and assists in database creation. Use when a user asks 'What database service should I use?', 'Help me pick a database', or when a user wants to create a new database on Google Cloud.…
cloud-sql-basics
This file generates or explains Cloud SQL resources. Use this file when the user asks to create a Cloud SQL instance or database for MySQL, PostgreSQL, or SQL Server. Cloud SQL manages third-party MySQL, PostgreSQL, and SQL Server instances as resources in Cloud SQL. For example, when Cloud SQL creates an open-source…
azure-resource-manager-mysql-dotnet
Azure MySQL Flexible Server SDK for .NET. Database management for MySQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "MySQL", "MySqlFlexibleServer", "MySQL Flexible Server", "Azure Database for MySQL", "MySQL database…
azure-mgmt-mongodbatlas-dotnet
Manage MongoDB Atlas Organizations as Azure ARM resources using Azure.ResourceManager.MongoDBAtlas SDK. Use when creating, updating, listing, or deleting MongoDB Atlas organizations through Azure Marketplace integration. This SDK manages the Azure-side organization resource, not Atlas clusters/databases directly.
azure-resource-manager-redis-dotnet
Azure Resource Manager SDK for Redis in .NET. Use for MANAGEMENT PLANE operations: creating/managing Azure Cache for Redis instances, firewall rules, access keys, patch schedules, linked servers (geo-replication), and private endpoints via Azure Resource Manager. NOT for data plane operations (get/set keys, pub/sub) …