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.
git clone --depth 1 https://github.com/pragunbhutani/dbt-llm-agentWrote 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.
[](https://agentmods.dev/rules/pragunbhutani/dbt-llm-agent/general-context-and-instructions)<a href="https://agentmods.dev/rules/pragunbhutani/dbt-llm-agent/general-context-and-instructions"><img src="https://agentmods.dev/badge/rules/pragunbhutani/dbt-llm-agent/general-context-and-instructions/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.
<a href="https://agentmods.dev/rules/pragunbhutani/dbt-llm-agent/general-context-and-instructions"><img src="https://agentmods.dev/badge/rules/pragunbhutani/dbt-llm-agent/general-context-and-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02253 | $0.02253 |
| Opus 5 | $0.01126 | $0.01126 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
general-context-and-instructions 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 11d 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 — 194 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. │ │ └── ... # 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. ├── mcp_server # FastMCP server (FastMCP is starlette not FastAPI) ├── 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
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.
- 11d ago First seen · 194 lines · 2,253 tokens per session scan A 83a466c5c651
general-context-and-instructions is a cursor rule published in the GitHub repository pragunbhutani/dbt-llm-agent (180 stars, last pushed 4d ago), licensed MIT. It adds 2,253 tokens to every session, about $0.0113 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 cursor rules, from other repositories
omni-rewriter
Omni-Rewriter prompt-expansion framework conventions.
prompt-design
Rules for changing the product’s AI prompts, including prompts for the CEO, workers, debates, skills, tools, facts, and on-screen text. They define where each instruction belongs and how to test prompt changes.
usually
Prompt Pocket — remembers your most-used prompts and lets you pick one to run instantly. Auto-records prompts you repeat >= 7 times across agent sessions, plus manual add/delete/edit/find. Pick-to-run and manual management work on every host; auto-scan covers Claude Code, Codex and OpenCode sessions. Use when the user…
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
ai-security
Security best practices for LLM/AI applications - prompt injection defense, rate limiting, PII protection.
latest-ai-models
Use only the latest AI models from all providers (updated Feb 2026).