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/entropy-data/dataproduct-builder-dbt/entropy-data-syncnpx skills add entropy-data/dataproduct-builder-dbt --skill entropy-data-syncgit clone --depth 1 https://github.com/entropy-data/dataproduct-builder-dbtWhat 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 | $0.00093 | $0.04597 |
| Opus 5 | $0.00046 | $0.02299 |
| Sonnet 5 | $0.00019 | $0.00919 |
| Haiku 4.5 | $0.00009 | $0.00460 |
Grade A, and why
entropy-data-sync 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entropy Data integration for dbt projects
Make sure a dbt project is well-integrated with Entropy Data.
What "well-integrated" means
A dbt project is well-integrated with Entropy Data when it has all of:
| # | Artifact | Path | Purpose |
|---|---|---|---|
| 1 | Open Data Product Specification | <data-product-id>.odps.yaml at repo root |
Declares the data product, team, output ports |
| 2 | Output-port data contracts | models/output_ports/v<N>/<contract-id>.odcs.yaml (one per output port — what this data product commits to produce) |
Schema + server config the contract test runs against; colocated with the SQL that implements it |
| 3 | Input-port data contracts | models/input_ports/<provider-output-port-id>.odcs.yaml (one per active access agreement — what this data product trusts upstream to produce) |
Cached snapshot of the upstream provider's ODCS; refreshed via entropy-data datacontracts get, never hand-edited |
| 4 | OpenLineage transport | openlineage.yml at repo root |
Makes dbt-ol run send lineage to api.entropy-data.com |
| 5 | Model layout | models/{input_ports,staging,intermediate,output_ports/v1}/ |
Convention that mirrors the data product's lifecycle |
| 6 | Publish workflow | .github/workflows/data-product.yml |
CI: dbt run/test → publish ODPS + output ODCS → run contract test |
| 7 | Git connections | One per ODPS + one per output-port ODCS, registered via entropy-data dataproducts gitconnection put and entropy-data datacontracts gitconnection put |
Lets Entropy Data link the published spec back to the YAML in the repo, and enables pull / push / push-pr from the CLI. Input-port ODCS files are not registered — they belong to the upstream data product, which owns its own git connection |
How to run this skill
Work in this exact order. Do not skip the audit.
${PLUGIN_ROOT}below refers to the root of this plugin — the directory that containsskills/. On Claude Code it is set automatically as${CLAUDE_PLUGIN_ROOT}— use that. On any other agent (Codex, Copilot CLI, etc.) it is unset; resolve it as../..relative to thisSKILL.mdfile's directory (i.e. the grandparent ofskills/<this-skill>/).
What ships with it
4 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.
- 3d ago First seen · 247 lines · 93 tokens per session scan A 25133a0cde67
entropy-data-sync is a skill published in the GitHub repository entropy-data/dataproduct-builder-dbt (12 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 4,597 once invoked, about $0.0005 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
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.