dataproduct-builder-dbt — Claude Code & Codex plugin: what it does
dataproduct-builder-dbt — a plugin for Claude Code and Codex that covers the full dbt data-product lifecycle: scaffold, implement models from a data contract, audit live data, and sync metadata to Entropy Data.
MIT ★ 1,596 updated 2026-10-29
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install dataproduct-builder-dbt@awesome-codex-pluginsWhat dataproduct-builder-dbt does
The plugin runs on Claude Code and Codex and ships seven skills. dataproduct-bootstrap generates a dbt project from scratch — dbt_project.yml, model directories, README, and profiles.yml.example. dataproduct-implement reads the input and output port contracts and writes the corresponding dbt models. datacontract-test runs datacontract test against live data to check schema and quality rules. entropy-data-sync migrates an existing dbt project to the Entropy Data reference layout, wires up a GitHub Actions workflow, and pushes all metadata.
Authentication against Entropy Data goes through the entropy-data CLI, which requires uv. Once dataproduct-bootstrap has scaffolded a project, run uv sync from the project root — both entropy-data and datacontract install into a per-project venv at pinned versions. The very first call to dataproduct-bootstrap runs in an empty directory with no pyproject.toml yet, so entropy-data must be available globally: install it with uv tool install --upgrade entropy-data and register a connection with your API key before that first run.
Teams with their own naming conventions can fork the repository. Templates under skills/dataproduct-bootstrap/templates/ and skills/entropy-data-sync/templates/ are drop-in replaceable — swap GitHub Actions for Airflow, change model layer names, or embed company tags.
What it helps with
- Scaffold a new dbt project following the organisation's conventions
- Implement dbt models from input and output data contracts
- Verify live data against schema and quality rules in a data contract
- Connect an existing dbt project to Entropy Data and configure GitHub Actions
- Strip PII columns from sample rows and upload the scrubbed dataset
Example prompts for the agent
- Implement the data product defined in
output_ports/v1/orders.odcs.yaml - Bootstrap a new dbt project for
customer-360and connect it to Entropy Data - Add the
is_premiumfield to the data contract and find input ports that can supply it
How to install dataproduct-builder-dbt
Plugin marketplace
/plugin marketplace add hashgraph-online/awesome-codex-plugins/plugin install dataproduct-builder-dbt@awesome-codex-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about dataproduct-builder-dbt
How do I install dataproduct-builder-dbt in Claude Code?
Run two commands in your terminal: first /plugin marketplace add hashgraph-online/awesome-codex-plugins, then /plugin install dataproduct-builder-dbt@awesome-codex-plugins.
What does the dataproduct-builder-dbt plugin do?
It gives your agent seven skills for dbt data-product work: project scaffolding, model generation from data contracts, live data quality checks, example-data scrubbing, and Entropy Data synchronisation.
What does the connection setup require before first use?
You need uv installed and entropy-data available globally via uv tool install --upgrade entropy-data. Register a connection with entropy-data connection add default --api-key <your-api-key> --host <your-entropy-data-host> before running dataproduct-bootstrap for the first time.
Source text
dataproduct-builder-dbt · MIT
# dataproduct-builder-dbt Skills for your favorite coding agent that helps you implement data products with [dbt](https://www.getdbt.com/), compliant to your organization's conventions, and fully integrated with [Entropy Data](https://entropy-data.com). <img width="1076" height="627" alt="Screenshot 2026-05-16 at 10 59 52" src="https://github.com/user-attachments/assets/026899ee-2a67-4b02-86e0-0e372be9b648" /> It also supports a contract-driven approach: specify your requirements as a [data contract](https://datacontract.com), and the builder implements the data product in minutes. ## Skills The plugin ships seven skills: - **[dataproduct-bootstrap](https://github.com/entropy-data/dataproduct-builder-dbt/blob/main/skills/dataproduct-bootstrap/SKILL.md)** scaffolds a new dbt data product from scratch: `dbt_project.yml`, model layout, README, `profiles.yml.example`, and more. - **[dataproduct-implement](https://github.com/entropy-data/dataproduct-builder-dbt/blob/main/skills/dataproduct-implement/SKILL.md)** analyzes the data product input and output data contract, and implements the dbt models. - **[dataproduct-exampledata](https://github.com/entropy-data/dataproduct-builder-dbt/blob/main/skills/dataproduct-exampledata/SKILL.md)** extracts sample rows, drops PII columns flagged in the contract (and obvious name-based PII), and uploads the scrubbed sample to Entropy Data. - **[datacontract-edit](https://github.com/entropy-data/dataproduct-builder-dbt/blob/main/skills/datacontract-edit/SKILL.md)** edits an output-port `models/output_ports/v<N>/*.odcs.yaml` using natural language. - **[datacontract-test](https://github.com/entropy-data/dataproduct-builder-dbt/blob/main/skills/datacontract-test/SKILL.md)** runs `datacontract test` to verify the live data still matches the schema and quality rules. - **[entropy-data-sync](https://github.com/entropy-data/dataproduct-builder-dbt/blob/main/skills/entropy-data-sync/SKILL.md)** integrate existing dbt project to the Entropy Data reference layout, set up GitHub Actions workflow, and synchronize all metadata. - **[entropy-data-teams](https://github.com/entropy-data/dataproduct-builder-dbt/blob/main/skills/entropy-data-teams/SKILL.md)** lists the teams configured in Entropy Data so the user can pick an owner. ## Install The skills are plain markdown, any coding agent that can read instruction files can run them. For major coding agents, those can be installed as a plugin: ### Claude Code In your terminal: ``` claude plugin marketplace add https://github.com/entropy-data/dataproduct-builder-dbt claude plugin install dataproduct-builder-dbt@dataproduct-builder-dbt -s project ``` ### OpenAI Codex In your terminal: ``` codex plugin marketplace add https://github.com/entropy-data/dataproduct-builder-dbt codex plugin add dataproduct-builder-dbt@dataproduct-builder-dbt ``` ### GitHub Copilot CLI In your terminal: ``` copilot plugin marketplace add https://github.com/entropy-data/dataproduct-builder-dbt copilot plugin install dataproduct-builder-dbt@dataproduct-builder-dbt ``` ### Other agents (Cursor, Aider, etc.) Any agent that reads `AGENTS.md` picks up the routing manifest. Alternatively, copy the `skills` to the directory that your coding agent expects. ### Connect The skills authenticate against Entropy Data through a connection registered with the [entropy-data CLI](https://github.com/entropy-data/entropy-data-cli) (requires [uv](https://docs.astral.sh/uv/)). The skills use a **per-project venv** for both `entropy-data` and `datacontract`. After `dataproduct-bootstrap` scaffolds a project, run `uv sync` from the project root to install both CLIs at the pinned versions, then invoke them as `uv run entropy-data …` / `uv run datacontract …`. The one exception is the first call to `dataproduct-bootstrap` itself, which runs against an empty directory (no `pyproject.toml`, no venv yet) and needs `entropy-data` available globally for its lookup step. Install once per machine: ``` uv tool install --upgrade entropy-data entropy-data connection add default --api-key <your-api-key> --host <your-entropy-data-host> ``` Create a user-scoped key in the Entropy Data web UI (**Organization Settings → API Keys → Create new API key**, scope `User (personal token)`). For CI workflows, add a connection with a team-scoped or organization-scoped API key. ## Use Ask the agent: > Implement the data product *url or id or new name*. Or: > Add the property *name* to the data contract and find data products that we could use as input ports. Request access and implement the dbt pipeline. ## Customization Organizations with their own data-product stack and naming conventions are encouraged to **fork or copy this repository** and adapt it to their environment. Common extension points: - **Templates** under [`skills/dataproduct-bootstrap/templates/`](skills/dataproduct-bootstrap/templates/) and [`skills/entropy-data-sync/templates/`](skills/entropy-data-sync/templates/) ship the ODPS, ODCS, OpenLineage transport, GitHub Actions workflow, and dbt project skeleton that the bootstrap and sync skills install. Replace any of them to match your conventions (e.g. swap GitHub Actions for Airflow, change the model layer naming, embed company-specific tags). - **Skills**: add your own `skills/<name>/SKILL.md` for stack-specific flows: specific skills for your data platform, internal data-quality checks, governance approvals, downstream sync to your data catalog, etc. Update `AGENTS.md` and `.github/copilot-instructions.md` so the routing tables surface them. - **Hooks**: extend [`hooks/hooks.json`](hooks/hooks.json) with additional `PostToolUse` validators (e.g. an internal lint on `models/**/*.sql`, or a check that team names match your IdP). - **Subagents**: add subagents under `agents/` for specialist roles (e.g. a PII scanner tuned to your classification taxonomy, a contract-review specialist for your terms-of-use boilerplate). After customizing, rename the plugin in [`.claude-plugin/plugin.json`](.claude-plugin/plugin.json) and [`.codex-plugin/plugin.json`](.codex-plugin/plugin.json), then publish under your own GitHub organization or GitLab repository. Update the installation instructions and usage instructions in Entropy Data. If a change you've made is broadly useful, [open an issue or PR upstream](https://github.com/entropy-data/dataproduct-builder-dbt/issues), generic improvements are very welcome. ## License MIT
© Entropy Data · MIT · hashgraph-online/awesome-codex-plugins