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 agentmods add skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-sparknpx skills add gemini-cli-extensions/data-agent-kit-starter-pack --skill gcp-sparkgit clone --depth 1 https://github.com/gemini-cli-extensions/data-agent-kit-starter-packWrote 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/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-spark)<a href="https://agentmods.dev/skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-spark"><img src="https://agentmods.dev/badge/skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-spark.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 | $0.00120 | $0.01453 |
| Opus 5 | $0.00060 | $0.00727 |
| Sonnet 5 | $0.00024 | $0.00291 |
| Haiku 4.5 | $0.00012 | $0.00145 |
Grade A, and why
gcp-spark 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 yesterday.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managed Spark on Google Cloud
[!IMPORTANT]
You MUST ALWAYS follow the Task Execution Workflow when writing spark code.
Task Execution Workflow
-
Understand schemas: ALWAYS use
@skill:discovering-gcp-data-assetsskill orreferences/schema_direct_inspection.mdto understand input and output schemas. Include the schema in your thought process BEFORE generating any code. Do NOT guess column names. Unless explicitly specified, assume that the assets are located in the same project. Avoid scanning for assets across other projects as it can take a long time. If an expected dataset or table does not exist, use@skill:discovering-gcp-data-assetsto discover all similar tables in the namespace or project.MINOR TYPO RULE: If there is a minor typo (e.g.
employeesvsemployee), you can fix the error and proceed.STRICT HALT RULE: If the discovered table names differ from the requested table by more than a minor typo (e.g. completely different words, prefixes, or suffixes), you must IMMEDIATELY report the missing table and a neutral list of all available alternatives in the same namespace to the user without making any recommendations. You MUST ask the user which alternative to use and then STOP EXECUTING your turn. Do NOT write any Spark code or notebooks. Do NOT proceed with code generation, do NOT add fallback logic to code, and do NOT automatically substitute any alternative table (even if its schema seems to match) without explicit user permission.
-
Verify source accessibility: verify access/existence using
gcloud storage ls gs://<path-to-dataset>. If accessing or reading a GCS path fails with a storage error e.g., permission errors like403 Forbidden/Forbidden/PermissionDenied, or location errors like404 Not Found/NotFound/FileNotFoundExceptionyou should report the error immediately. Either (1) ask the user what to do next, or (2) if asked to execute a notebook, save the notebook with the error output and recommend next steps to resolve the issue. Do NOT scan all buckets for alternative fallback datasets when encountering GCS errors. -
Generate spark code:
What ships with it
5 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.
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.
- yesterday Changed · +9 tokens per session e7300fac0d39
- 4d ago Changed · +2 lines 1da125eac0c3
- 6d ago First seen · 127 lines · 111 tokens per session scan A 6840591bebdd
gcp-spark is a skill published in the GitHub repository gemini-cli-extensions/data-agent-kit-starter-pack (179 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 1,453 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 2026-08-30.
Other skills, from other repositories
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).
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.