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 instructions/entropy-data/dataproduct-builder-dbt/agents-mdgit 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 | $0.01196 | $0.01196 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
dataproduct-builder-dbt AGENTS.md 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dataproduct-builder-dbt — agent manifest
This file is the plugin's authoritative routing manifest, not a template. It lives at the plugin's repo root and is meant to be referenced from your project (e.g. via Codex CLI's marketplace install, or a one-line pointer in your project's own
AGENTS.md), not copied into your project. Updating the plugin updates this file in place.
This repository is a coding-agent plugin that helps build dbt data products and integrate them with Entropy Data. It exposes its capabilities as skills — markdown files under skills/<name>/SKILL.md that you read top-to-bottom and execute step by step.
When a user request matches a skill's trigger, read the corresponding SKILL.md start to finish before acting. Each skill contains audit steps, parameter-gathering, and explicit user-confirmation gates that must not be skipped.
Skills
| When the user asks about… | Follow this skill |
|---|---|
| Scaffolding a brand-new dbt data product from scratch (greenfield, empty directory) | skills/dataproduct-bootstrap/SKILL.md |
| Auditing an existing dbt project against the Entropy Data layout and adding what's missing (ODPS, ODCS, OpenLineage, GitHub Actions, git connections) | skills/entropy-data-sync/SKILL.md |
| Implementing a data product from a published Entropy Data URL or id — derive dbt output-port models from the ODCS schema | skills/dataproduct-implement/SKILL.md |
Editing an output-port data contract (models/output_ports/v<N>/*.odcs.yaml) and testing whether the change is breaking |
skills/datacontract-edit/SKILL.md |
Testing existing data contracts against the live warehouse (no edits — just run datacontract test) |
skills/datacontract-test/SKILL.md |
| Uploading example / sample rows for a data product to Entropy Data | skills/dataproduct-exampledata/SKILL.md |
Listing teams in Entropy Data (e.g. to pick TEAM_NAME as the data product owner) |
skills/entropy-data-teams/SKILL.md |
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 · 45 lines · 1,196 tokens per session scan A 209329efba3f
dataproduct-builder-dbt AGENTS.md is an instructions file published in the GitHub repository entropy-data/dataproduct-builder-dbt (12 stars, last pushed 3mo ago), licensed MIT. It adds 1,196 tokens to every session, about $0.0060 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 instructions, from other repositories
pgContext AGENTS.md
Instructions for Evokoa/pgContext, covering agents.md — installing & using pgcontext with an ai agent, what pgcontext is (and why it's worth using), environment facts (pins — do not guess), path a — docker (preferred; zero build, most deterministic) and path b — build from source (when docker is unavailable).
ai-toolkit AGENTS.md
Instructions for memgraph/ai-toolkit, covering agents.md, what this repo is, repository layout, the context graph family (context-graph/) and environment & setup.
flock copilot-instructions.md
Instructions for dais-polymtl/flock, covering copilot instructions for flock, repository layout, building, setup vcpkg (first time or after clean) and release build.
pdf-brain AGENTS.md
Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.
duckrun AGENTS.md
Instructions for djouallah/duckrun, covering agents.md and working on duckrun itself.
markdown-vdb CLAUDE.md
Instructions for geckse/markdown-vdb, covering markdown vdb, architecture, project structure, core design decisions and key conventions.