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 sfc-gh-dflippo/snowflake-dbt-demo --skill worker-k8s-externalgit clone --depth 1 https://github.com/sfc-gh-dflippo/snowflake-dbt-demoWrote 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/worker-k8s-external)<a href="https://agentmods.dev/skills/sfc-gh-dflippo/snowflake-dbt-demo/worker-k8s-external"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/worker-k8s-external/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/worker-k8s-external"><img src="https://agentmods.dev/badge/skills/sfc-gh-dflippo/snowflake-dbt-demo/worker-k8s-external.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 | $0.00056 | $0.02304 |
| Opus 5 | $0.00028 | $0.01152 |
| Sonnet 5 | $0.00011 | $0.00461 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
worker-k8s-external 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worker Kubernetes Setup — External Cluster
Deploy the Data Exchange Worker as a Kubernetes Deployment on a customer-managed cluster. Unlike SPCS, there is no injected Snowflake token — both source database and Snowflake credentials are supplied explicitly via Kubernetes Secrets.
Step 1 — Image Version
The worker image version is pinned to your scai CLI release — do not use SHOW IMAGES to pick the latest tag, as it may be incompatible with this version of the CLI.
Get the pinned version by running:
scai data worker setup --compute-pool <any-pool>
The CLI logs: Using pinned Data Exchange Worker image: /snowflake/images/snowflake_images/data-exchange-worker:<version>
Record that exact version tag (e.g., 1.11.1). Use it as <version> in all subsequent steps. You can cancel the setup command once you have the version — this step is only needed to read the tag from CLI output. Upgrading the version later requires re-running this skill from the beginning.
Note: The image tag is a version number (e.g., 1.12.0), not a platform identifier. The source type is controlled by the DATA_SOURCE_TYPE environment variable. Read it from the project's scai source connection:
| Source system | DATA_SOURCE_TYPE |
|---|---|
| SQL Server | sqlserver |
| Redshift | redshift |
| Oracle | oracle |
| Teradata | teradata |
| PostgreSQL | postgresql |
Step 2 — Affinity Label
In all steps below, substitute every <placeholder> token with its actual value — never output a literal <placeholder> string. Key substitutions:
<label>— the affinity label confirmed in this step<version>— the image version from Step 1<source_type>,<host>,<port>,<database>— from the project's scai source connection<replica_count>— the count the user provides in Step 3<source_username>,<source_password>— source database credentials from the project's scai source connection; do not ask the user to type these in the chat — instruct them to fill them directly into the command<snowflake_account>,<snowflake_user>,<snowflake_password>,<warehouse>— Snowflake credentials collected from the user in Step 4; do not ask the user to say passwords in the chat — instruct them to fill them directly into the command
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 · 241 lines · 0 tokens per session scan A 3c81d75b276f
worker-k8s-external 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 56 tokens to every session and 2,304 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 2026-09-10.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.