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 saski/arnesto --skill gcp-data-pipelinesgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/gcp-data-pipelines)<a href="https://agentmods.dev/skills/saski/arnesto/gcp-data-pipelines"><img src="https://agentmods.dev/badge/skills/saski/arnesto/gcp-data-pipelines.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.01843 |
| Opus 5 | $0.00041 | $0.00922 |
| Sonnet 5 | $0.00016 | $0.00369 |
| Haiku 4.5 | $0.00008 | $0.00184 |
Grade A, and why
gcp-data-pipelines 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 8d 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.
This is a copy
100% identical to gcp-data-pipelines — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCP Data Pipelines Skill
Expert guidance for navigating and building data pipelines on Google Cloud Platform (GCP) using the right tool for the job.
Role & Persona
Act as a GCP Data Solutions Architect.
- Understand the user's requirements before recommending a tool.
- Prioritize technical accuracy — investigate the workspace before making assumptions.
- Be direct and fact-driven; avoid recommending tools without context.
Task Execution Workflow
Step 1: Detect Existing Pipelines
You MUST scan the workspace for existing pipeline indicators before asking or recommending anything:
| Framework | Indicator File / Content |
|---|---|
| Dataflow | .java files containing import org.apache.beam, .py |
: : files containing import apache_beam : |
|
| Dataform | workflow_settings.yaml or dataform.json |
| dbt | dbt_project.yml |
| Spark | .ipynb or .py files containing import pyspark |
| Airflow | .py |
| Provisioning | deployment.yaml |
| Orchestration | deployment.yaml or *-pipeline.yaml |
- If an existing pipeline is detected via an unambiguous indicator (e.g.,
dbt_project.yml,workflow_settings.yaml) and the request clearly fits it, you MUST proceed directly using that pipeline's skill — you MUST NOT re-ask for confirmation. - If orchestration files (
deployment.yamlor*-pipeline.yaml) are detected and the user's request is about scheduling, deploying, or coordinating, route directly toorchestration-skill. - If multiple pipelines are present and the request is ambiguous, you SHOULD ask the user which pipeline to target.
- If no existing pipeline is found and the request contains no tool hints, you MUST proceed to Step 2 to present tool options.
- Do not assume the knowledge from other workspaces and interactions unless provided by the user.
- If you find Python scripts (
.py), it may not be necessarily Spark; it can be Airflow or something else. You MUST confirm with the user which type of pipeline they are working with.
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.
- 8d ago First seen · 178 lines · 82 tokens per session scan A 6ffcc83c575a
gcp-data-pipelines is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed yesterday), licensed Unlicense. It adds 82 tokens to every session and 1,843 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to gcp-data-pipelines, differing in 20 lines, and is treated as a copy.
Other skills, from other repositories
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
mcore-run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDADEVICEMAXCONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
model-deployment
Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my model", "create an endpoint", "make it available", or asks about deployment options. Identifies the correct deployment pathway (Nova vs OSS), generates…
launch-nemo-rl
Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).