gcp-dataflow

gcp-dataflow is a skill for Claude Code, Codex from gemini-cli-extensions/data-agent-kit-starter-pack. It costs 207 tokens per session (4,764 once invoked), scanned A, original, Apache-2.0.

A guide to building and running Apache Beam data-processing pipelines on Google Cloud Dataflow. Apache Beam is a framework for processing data in batches or continuously.

In plain words
What is it for?
Use it to write Java, Python, or Go pipelines, configure Flex Templates, connect Cloud Build, and troubleshoot Dataflow jobs.
Why use it?
Creating a pipeline from scratch may be unnecessary, and jobs can fail because of packaging, configuration, or runtime problems. This guide helps check existing templates and investigate job health.

Skill for Claude CodeCodex

Part of the dak plugin — 29 skills, 13 MCP servers shipped together

Install

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.

agentmods
npx agentmods add skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-dataflow
Any agent
npx skills add gemini-cli-extensions/data-agent-kit-starter-pack --skill gcp-dataflow
Clone the repo
git clone --depth 1 https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack

Made for: Claude Code, Codex.

Or install dak, the plugin that ships this one along with the rest of its 29 skills, 13 MCP servers.

Wrote 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.

agentmods badge for gcp-dataflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-dataflow.svg)](https://agentmods.dev/skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-dataflow)
Your own site
<a href="https://agentmods.dev/skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-dataflow"><img src="https://agentmods.dev/badge/skills/gemini-cli-extensions/data-agent-kit-starter-pack/gcp-dataflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 207 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,764 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00207 $0.04764
Opus 5 $0.00103 $0.02382
Sonnet 5 $0.00041 $0.00953
Haiku 4.5 $0.00021 $0.00476

Measured 5d ago against content hash 85a57595c1b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gcp-dataflow 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 5d 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.

skills/gcp-dataflow/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apache Beam Pipelines on Cloud Dataflow

Pipeline authoring

Use this section when implementing Dataflow pipeline logic using Apache Beam.

Check if existing Google Dataflow Template exists

Google provides a variety of pre-built, open source Dataflow templates that can be used for common scenarios. Before implementing a pipeline from scratch, you MUST follow the steps below to check whether a Dataflow template for the pipeline logic you need to implement already exists.

  • Step 1: Check for a matching Google Dataflow Template

    • Identify the source and sink (e.g., GCS to BigQuery) from the user's request. Note: You MUST NOT proceed until the source and sink are clearly identified.
    • Action: List templates in the public dataflow-templates bucket:
      • For Classic templates, check gs://dataflow-templates/latest.
      • For Flex templates, check gs://dataflow-templates/latest/flex. Use gcloud storage ls to list the contents.
    • Match templates by name or description to the source and sink.
    • If no matching template is found, go to Create a new pipeline from scratch.
  • Step 2: Confirm template selection

    • Present the matched template(s) to the user with a brief explanation of why they match, and make a note of whether it is a Classic or Flex template.
    • Action: Ask the user for explicit confirmation to proceed with this template.
    • If the user rejects or prefers a custom solution, proceed to Create a new pipeline from scratch.

Create a new pipeline from scratch

Use this section when creating a new project for a Dataflow pipeline from scratch.

  • If the user doesn't say explicitly which language (Java, Python, Go) shall be used to write the pipeline, you MUST confirm the language.
  • Determine which version of Beam SDK should be used by searching for the most recently released version of Apache Beam, unless the user already uses a particular version.
    • Action: Run a web search for the latest Apache Beam SDK release.
  • YOU MUST use same version of Apache Beam consistently throughout the project in Dockerfiles, requirements.txt, and other similar files where versions are specified.

Read the full file on GitHub · 419 lines

Changes

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.

  1. 5d ago First seen · 419 lines · 207 tokens per session scan A 85a57595c1b0

Subscribe to this mod's changes

gcp-dataflow is a skill published in the GitHub repository gemini-cli-extensions/data-agent-kit-starter-pack (178 stars, last pushed yesterday), licensed Apache-2.0. It adds 207 tokens to every session and 4,764 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

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/skills · 64 tokens

application-design-center-design-deploy

Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…

google/skills · 94 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

yandex-cloud

Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.

Tracer-Cloud/opensre · 71 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens