AutoRAG Agent is a librarian-style system that searches files on a computer, checks the original documents, and organizes findings into numbered knowledge units using multiple retrieval methods. It helps an agent answer questions from local documents without first copying them into a centralized vector database, while the repository also maintains the earlier AutoRAG tool for optimizing retrieval-augmented-generation pipelines. The catalogue entries provide skills and instructions for working with AutoRAG Agent.
Borrowing it
Nothing to install: this file belongs to Marker-Inc-Korea/AutoRAG. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Marker-Inc-Korea/AutoRAG/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/Marker-Inc-Korea/AutoRAGWrote 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/instructions/marker-inc-korea/autorag/copilot-instructions)<a href="https://agentmods.dev/instructions/marker-inc-korea/autorag/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/marker-inc-korea/autorag/copilot-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/instructions/marker-inc-korea/autorag/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/marker-inc-korea/autorag/copilot-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 | $0.03237 | $0.03237 |
| Opus 5.5 | $0.01295 | $0.01295 |
| Sonnet 5.5 | $0.00647 | $0.00647 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade D, and why
AutoRAG copilot-instructions.md scanned grade D with 3 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get update Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Install UV package manager for faster dependency management: `curl -LsSf https://astral.sh/uv/install.sh | sh` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Install UV package manager for faster dependency management: `curl -LsSf https://astral.sh/uv/install.sh | sh` How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AutoRAG - AI-Powered RAG Pipeline Optimization
NOTE (monorepo layout): These instructions describe the legacy Python AutoRAG, which now lives in the
legacy/directory of this repository. Run all commands below fromlegacy/. The repository root hosts AutoRAG 2.0, a TypeScript/Bun librarian agent (src/,test/,package.json).
AutoRAG is a Python package for automatically finding optimal RAG (Retrieval-Augmented Generation) pipelines for your data using AutoML techniques. The system evaluates various RAG module combinations to find the best configuration for your specific use case.
ALWAYS reference these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.
Working Effectively
Prerequisites and System Setup
- CRITICAL: Use Python 3.10 or higher (Python 3.12 recommended)
- Install UV package manager for faster dependency management:
curl -LsSf https://astral.sh/uv/install.sh | sh - For systems without UV, fallback to pip installation
- Install system dependencies first (see Platform Dependencies section)
Platform Dependencies
Install these system packages before building AutoRAG:
Ubuntu/Debian:
sudo apt-get update
sudo apt-get install -y build-essential gcc poppler-utils tesseract-ocr libssl-dev
Java (required for some features):
# Install Java 17 (required)
sudo apt-get install openjdk-17-jdk
Bootstrap, Build, and Test - COMPLETE WORKFLOW
TIMING EXPECTATIONS:
- NEVER CANCEL builds or tests - they can take 15-45+ minutes
- Initial dependency installation: 15-30 minutes
- Full test suite: 15-20 minutes
- Documentation build: 5-10 minutes
- ALWAYS set timeouts to 60+ minutes for builds and 30+ minutes for tests
1. Clone and Environment Setup:
git clone https://github.com/Marker-Inc-Korea/AutoRAG.git
cd AutoRAG/autorag
2. Create Virtual Environment and Install (Primary Method - UV):
# Install UV if not available
curl -LsSf https://astral.sh/uv/install.sh | sh
source ~/.bashrc # Reload shell
# Create virtual environment and install
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install AutoRAG with all extras - TAKES 15-30 MINUTES, NEVER CANCEL
uv pip install -r pyproject.toml --all-extras -e . --timeout 3600
# Install development dependencies - TAKES 5-10 MINUTES
uv pip install --group dev --timeout 1800
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.
- 1mo ago First seen · 320 lines · 3,237 tokens per session scan D 291cb7dc2d36
AutoRAG copilot-instructions.md is an instructions file published in the GitHub repository Marker-Inc-Korea/AutoRAG (5,191 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,237 tokens to every session, about $0.0129 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.