dbt-llm-agent: Instructions file for Claude Code

CLAUDE.md

dbt-llm-agent CLAUDE.md is an instructions file for Claude Code from pragunbhutani/dbt-llm-agent. It costs 2,285 tokens per session, scanned A, original, MIT.

Repository instructions for a dbt-focused AI data analyst. dbt is a tool for managing and transforming analytics data, while a monorepo is one repository containing several related projects or services.

In plain words
What is it for?
Use them when changing the monorepo, dbt Cloud or GitHub connections, data-warehouse access, chat interfaces, Slack or MCP integrations, or analytics answers such as queries and charts.
Why use it?
They provide the project context and boundaries needed to make design decisions in a repository that connects data sources, AI workflows, and several user interfaces.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Cursor.

This is pragunbhutani/dbt-llm-agent's own configuration. It tells Claude Code how to work on dbt-llm-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dbt-llm-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pragunbhutani/dbt-llm-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pragunbhutani/dbt-llm-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pragunbhutani/dbt-llm-agent

Made for: Claude Code.

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 dbt-llm-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pragunbhutani/dbt-llm-agent/claude-md/github.svg)](https://agentmods.dev/instructions/pragunbhutani/dbt-llm-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pragunbhutani/dbt-llm-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/pragunbhutani/dbt-llm-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dbt-llm-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pragunbhutani/dbt-llm-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/pragunbhutani/dbt-llm-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,285 This file is loaded in full into every session.
When invoked 2,285 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02285 $0.02285
Opus 5 $0.01143 $0.01143
Sonnet 5 $0.00457 $0.00457
Haiku 4.5 $0.00229 $0.00229

Measured 10d ago against content hash d6f0119b7d7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dbt-llm-agent CLAUDE.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 10d 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.

CLAUDE.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Description

We are building an LLM powered AI data analyst for Data Engineering teams that work with dbt to manage their analytics code bases. To use this project, users should be able to connect with their dbt cloud projects or their dbt core github repos via an interface which is then used to build a knowlege base. We then use various AI based workflows to allow users to ask questions about their data and then surface the queries, charts or insights needed to answer their data questions.

We will enable interaction through a variety of interfaces including Slack, MCP connectivity with LLM apps, a streaming chat interface and maybe even more in future.

We will also allow users to connect our app with their data warehouses so we can try and answer their questions directly, and support our answers with charts and visualisations etc. If not, we should surface the queries users can use to answer their questions.

We may add more functionality in future or get rid of some of the functionality I've mentioned. I've shared this information for context but we may not be building all of these things at once.

Ask clarifying questions and give your feedback on design decisions objectively - there is no need to agree with every design decision I propose, feel free to provide constructive feedback.

Monorepo Structure

The project is a monorepo that looks something like this:

/ragstar-project-root/ ├── backend_django/ # Django application (moved from root) │ ├── manage.py │ ├── ragstar/ # Django settings directory │ ├── apps/ # Django apps │ │ ├── accounts # user accounts, organisations, org settings etc. │ │ ├── data_sources # connection to knowledge sources like dbt │ │ ├── embeddings # storing and retrieving embeddings │ │ ├── integrations # integrations to external tools like slack, metabase etc. │ │ ├── knowledge_base # information about our dbt projects, models, questions etc. │ │ ├── llm_providers # interface for interacting with LLM provider APIs │ │ ├── workflows # all workflows, agentic or not │ │ │ ├── workflow_name # each workflow has a workflow.py, prompts.py etc. │ │ ├── mcp_server # FastMCP application which works with Django asgi │ │ └── ... # More apps may be found here │ ├── static/ │ ├── pyproject.toml # Python dependencies │ ├── uv.lock # Lock file │ ├── .python-version # Python version specification │ └── Dockerfile # Backend-specific Docker config ├── frontend_nextjs/ # Renamed from client/ - ready for Next.js │ ├── public/ # Public static assets │ ├── src/ │ │ ├── app/ # Next JS App router project structure │ │ │ ├── (auth)/ # Signin and Signup pages │ │ │ ├── dashboard/ # Dashboard pages │ │ │ ├── ... │ │ ├── components/ # Creates reusable react components │ │ └── ... # Other reusable utilities should be placed here │ └── ... # NextJS, Typescript, package.json, eslint etc. ├── config_examples/ # Config examples like .slack_manifest.example.json, .ragstarrules.example.yml ├── docs/ # GitHub Pages docs (unchanged) ├── docker-compose.yml # Orchestrates all services ├── .env.example # Example environment file └── .env # Shared environment variables

Read the full file on GitHub · 175 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. 10d ago First seen · 175 lines · 2,285 tokens per session scan A d6f0119b7d7f

Subscribe to this mod's changes

dbt-llm-agent CLAUDE.md is an instructions file published in the GitHub repository pragunbhutani/dbt-llm-agent (180 stars, last pushed 4d ago), licensed MIT. It adds 2,285 tokens to every session, about $0.0114 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens