overview

Project rules for Openground, a tool that collects official framework and library documentation, stores it in a searchable local database, and lets AI coding agents query it.

In plain words
What is it for?
Use them when developing or reviewing Openground's documentation-ingestion pipeline, local search database, or agent-facing search server.
Why use it?
They provide shared expectations for simple code, required type hints, useful error messages, and focused documentation, making the project easier to maintain.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/poweroutlet2/openground/overview
Clone the repo
git clone --depth 1 https://github.com/poweroutlet2/openground

Made for: Cursor.

Per session 581 This file is loaded in full into every session.
When invoked 581 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00581 $0.00581
Opus 5 $0.00291 $0.00291
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 2d ago against content hash 216c2ffdb1f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

overview 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 2d 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.

.cursor/rules/overview.mdc · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Openground Project Configuration

Project Overview

Openground is a tool for extracting framework and library documentation from official sources (sitemaps and git repos) and making it queryable by AI coding agents. It consists of:

  1. RAG documentation ingestion pipeline: Extracts documentation from sources (sitemap.xml or git repos), stores pages as structured JSON, then chunks and embeds them into a local LanceDB database.
  2. MCP server: Exposes tools for AI agents to perform hybrid semantic and BM25 search over the documentation database.

The philosophy mandates simplicity of implementation for maintainers and ease of use for users.

Coding Style

  • Paradigm: Functional programming preferred
  • Type Hints: Required for all functions
  • Error Handling: Errors must provide clear and actionable logging. Fail fast with actionable error messages.
  • Documentation:
    • Concise but informative docstrings for functions
    • Prefer self-commenting code
    • Inline comments only for particularly confusing lines
  • Comments: Do not add comments that a human would not add. Do not add excessive comments. Do not add comments to parts of the code you are not working on.

Directory Structure

Openground is a RAG pipeline tool with CLI and MCP server components.

  • Main modules: cli.py, config.py, ingest.py, query.py, server.py, embeddings.py, console.py
  • extract/ subdirectory: git.py, source.py, common.py, sitemap.py
  • Configuration: Managed via JSON config file (see config.py)
  • Pipeline: extract → embed → query (hybrid semantic + BM25 search in lancedb)

Behavioral Rules

  • Explanation: Explain "why" before coding
  • File Size: No file size preference
  • Comments: Only modify existing comments when touching related code
  • Errors: Fail fast with actionable error messages

Project Commands

Development

uv run python ...             # Run commands with venv
uv run ruff check .    # Linting
uv run ty check .      # Type checking

Read the full file on GitHub · 61 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. 2d ago First seen · 61 lines · 581 tokens per session scan A 216c2ffdb1f4

Subscribe to this mod's changes

overview is a cursor rule published in the GitHub repository poweroutlet2/openground (54 stars, last pushed 5mo ago), licensed MIT. It adds 581 tokens to every session, about $0.0029 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.