Skip to content
Back to search

data-agent-kit-plugin

Your entire data stack in your favorite agentic tool.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/GoogleCloudPlatform/data-agent-kit-plugin with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/GoogleCloudPlatform/data-agent-kit-plugin'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/googlecloudplatform--data-agent-kit-plugin/badge.svg)](/listings/googlecloudplatform--data-agent-kit-plugin)

HTML

<a href="/listings/googlecloudplatform--data-agent-kit-plugin"><img src="/api/listings/googlecloudplatform--data-agent-kit-plugin/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

<details> <summary><b>Antigravity CLI</b></summary>

agy plugin install https://github.com/GoogleCloudPlatform/data-agent-kit-plugin

</details>

<details> <summary><b>Claude Code</b></summary>

claude plugin marketplace add https://github.com/GoogleCloudPlatform/data-agent-kit-plugin
claude plugin install dak@dak-marketplace

</details>

<details> <summary><b>Codex CLI</b></summary>

codex plugin marketplace add GoogleCloudPlatform/data-agent-kit-plugin
codex plugin add dak@dak-marketplace

</details>

<details> <summary><b>Any Agent Plugins–compatible client</b></summary>

Point your client's plugin install command at this repository:

https://github.com/GoogleCloudPlatform/data-agent-kit-plugin

See your agent's documentation for the exact command.

</details>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 13 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "dak-marketplace",
  3. "owner": {
  4. "name": "Google LLC"
  5. },
  6. "plugins": [
  7. {
  8. "name": "dak",
  9. "source": "./",
  10. "description": "This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem."
  11. }
  12. ]
  13. }
README.md · README · 211 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Data Agent Kit
  2. Data Agent Kit is a **free** plugin that connects your coding agent to 15+
  3. Google Data Cloud services, including BigQuery, Cloud Storage, Spanner,
  4. AlloyDB, Managed Service for Apache Spark, and Knowledge Catalog.
  5. Spend your time on insights, not boilerplate. Describe a data task in plain
  6. language, and watch your agent handle the heavy lifting for you: writing SQL
  7. queries, building notebooks, generating pipeline code, setting up ML workflows,
  8. and more.
  9. > [!IMPORTANT]
  10. > This repository contains the Data Agent Kit **plugin** for coding agents:
  11. > Antigravity CLI, Claude Code, Codex CLI, and any
  12. > [Agent Plugins](https://github.com/agentplugins/agent-plugins-spec)–compatible
  13. > client.
  14. >
  15. > If you use an IDE, install the Data Agent Kit **extension** instead. If you
  16. > use **Visual Studio Code**, install Data Agent Kit from the
  17. > [Visual Studio Marketplace](https://marketplace.visualstudio.com/items?itemName=GoogleCloudTools.datacloud).
  18. > If you use another VS Code-based IDE, such as **Antigravity IDE** or **Cursor**,
  19. > search for "Data Agent Kit" in your IDE's Extensions panel and install it from
  20. > there.
  21. ## Prerequisites
  22. - A supported coding agent: Antigravity CLI, Claude Code, Codex CLI, or another Agent Plugins–compatible client.
  23. - **Node.js** (latest LTS recommended).
  24. - **Google Cloud CLI (`gcloud`)**, installed and authenticated:
  25. 1. [Install the gcloud CLI](https://cloud.google.com/sdk/docs/install).
  26. 2. Log in with your Google Cloud account:
  27. ```bash
  28. gcloud auth login
  29. ```
  30. 3. Log in to
  31. [Application Default Credentials (ADC)](https://cloud.google.com/docs/authentication/provide-credentials-adc):
  32. ```bash
  33. gcloud auth application-default login
  34. ```
  35. ## Installation
  36. <!-- {x-release-please-start-version} -->
  37. <details>
  38. <summary><b>Antigravity CLI</b></summary>
  39. ```bash
  40. agy plugin install https://github.com/GoogleCloudPlatform/data-agent-kit-plugin
  41. ```
  42. </details>
  43. <details>
  44. <summary><b>Claude Code</b></summary>
  45. ```bash
  46. claude plugin marketplace add https://github.com/GoogleCloudPlatform/data-agent-kit-plugin
  47. claude plugin install dak@dak-marketplace
  48. ```
  49. </details>
  50. <details>
  51. <summary><b>Codex CLI</b></summary>
  52. ```bash
  53. codex plugin marketplace add GoogleCloudPlatform/data-agent-kit-plugin
  54. codex plugin add dak@dak-marketplace
  55. ```
  56. </details>
  57. <details>
  58. <summary><b>Any Agent Plugins–compatible client</b></summary>
  59. Point your client's plugin install command at this repository:
  60. ```text
  61. https://github.com/GoogleCloudPlatform/data-agent-kit-plugin
  62. ```
  63. See your agent's documentation for the exact command.
  64. </details>
  65. ## Configuration
  66. <details>
  67. <summary><b>Antigravity CLI and Claude Code</b></summary>
  68. Provide any prompt to your agent and it will walk you through configuring
  69. Data Agent Kit.
  70. Alternatively, you can manually invoke the Data Agent Kit setup skill:
  71. ```text
  72. /dak:dak-setup
  73. ```
  74. Restart your agent when prompted to complete the setup.
  75. </details>
  76. <details>
  77. <summary><b>Codex CLI</b></summary>
  78. Codex runs with a sandbox by default that prevents Data Agent Kit from
  79. configuring itself. Temporarily disable the sandbox to allow setup:
  80. ```bash
  81. codex -s danger-full-access
  82. ```
  83. Invoke the Data Agent Kit setup skill:
  84. ```text
  85. $dak:dak-setup
  86. ```
  87. Restart your agent when prompted to complete the setup. You can now use Codex
  88. normally with the sandbox enabled.
  89. </details>
  90. <!-- {x-release-please-end} -->
  91. <!-- github-release-force: 1.3.0 -->
  92. ## Features and Common Uses
  93. - **Data engineering:** Build pipelines that turn source data into
  94. analysis-ready tables, with quality checks along the way. Develop
  95. transformations with dbt or Dataform, schedule workflows with Managed Service
  96. for Apache Airflow, and debug failed runs by tracing execution logs and code.
  97. - **Data science:** Develop experiments in Jupyter notebooks on local Python or
  98. remote Managed Service for Apache Spark kernels. Prepare features from
  99. BigQuery, train models with BigQuery ML, and schedule batch inference.
  100. - **Data analysis:** Explore data across BigQuery, AlloyDB, and Cloud SQL. Find
  101. datasets with Knowledge Catalog, guided by data quality metrics and lineage,
  102. then build visualizations or reusable data models.
  103. ## Example Prompts
  104. - "Create a PySpark notebook to train a distributed Random Forest model on the
  105. BigQuery table `my_transactions`
  106. - "Find datasets about customer orders in Knowledge Catalog and show their
  107. lineage"
  108. - "Create an Airflow DAG that runs the dedup notebook, the dbt pipeline, and
  109. model training every Monday morning.
  110. - "My last Dataflow job failed. Find the root cause in the logs and propose a
  111. fix"
  112. ## Troubleshooting
  113. If you see `could not find default credentials` or other auth errors, ensure you
  114. are logged into gcloud.
  115. Exit your agent, run `gcloud auth login` followed by
  116. `gcloud auth application-default login`, then restart your agent.
  117. ## Security
  118. Your agent can run tools and commands on your behalf. Apply the **principle of
  119. least privilege** to every CLI, MCP server, and resource it can access:
  120. - Use
  121. [service account impersonation](https://cloud.google.com/docs/authentication/use-service-account-impersonation)
  122. instead of end-user credentials.
  123. - Grant the service account only the
  124. [roles it needs](https://cloud.google.com/iam/docs/roles-overview).
  125. - Use
  126. [Principal Access Boundary policies](https://cloud.google.com/iam/docs/principal-access-boundary-policies#use-case-one-project)
  127. with a condition in the policy binding to restrict your agent's service
  128. accounts to intended projects.
  129. Learn how to
  130. [mitigate prompt injection risks](https://docs.cloud.google.com/data-cloud-extension/vs-code/prompt-injection-risk)
  131. with Google Cloud MCP.
  132. ## Usage Statistics
  133. Data Agent Kit collects usage statistics (such as when included skills and MCP
  134. tools are used) to improve reliability and performance. No user code, file
  135. contents, or application data values are collected.
  136. To opt out, either set `DO_NOT_TRACK=1` in your environment:
  137. ```bash
  138. export DO_NOT_TRACK=1
  139. ```
  140. Or create or update `~/.data_agent_kit/config.json`:
  141. ```json
  142. {
  143. "enableTelemetry": false
  144. }
  145. ```
  146. ## Feedback
  147. We want your feedback! Please
  148. [open an issue](https://github.com/GoogleCloudPlatform/data-agent-kit-plugin/issues/new)
  149. to report bugs, file feature requests, or ask questions.
  150. ## Resources
  151. - [Data Agent Kit homepage](https://cloud.google.com/products/data-agent-kit)
  152. - [Data Agent Kit documentation](https://docs.cloud.google.com/data-agent-kit)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.