What is gpt-rag-ingestion copilot-instructions.md?

Repository instructions for Azure's GPT-RAG ingestion project, a system that turns source documents into searchable pieces and stores them in Azure AI Search. They cover branches, version numbers, changelogs, and release procedures.

Use them when choosing branches, writing commits, changing versions, updating changelogs, preparing releases, or modifying ingestion code.

They reduce mistakes when developing, reviewing, and releasing changes to the document-ingestion system.

How Azure/gpt-rag-ingestion configures GitHub Copilot

About the project

GPT-RAG Data Ingestion is a service that processes documents such as PDFs, images, spreadsheets, transcripts, and SharePoint files so they can be searched through Azure AI Search. It prepares data with format-specific chunking and text or image embeddings for multimodal retrieval in agent-based applications.

Azure/gpt-rag-ingestion · 189 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to Azure/gpt-rag-ingestion. 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/Azure/gpt-rag-ingestion/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/Azure/gpt-rag-ingestion

Made for: GitHub Copilot.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/azure/gpt-rag-ingestion/copilot-instructions.svg)](https://agentmods.dev/instructions/azure/gpt-rag-ingestion/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/azure/gpt-rag-ingestion/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azure/gpt-rag-ingestion/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>

Per session 968 This file is loaded in full into every session.

When invoked 968 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.

Model	Per session	Once invoked
Fable 5.1	$0.00968	$0.00968
Opus 5	$0.00484	$0.00484
Sonnet 5	$0.00194	$0.00194
Haiku 4.5	$0.00097	$0.00097

Measured 4d ago against content hash 0340f9ba1b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gpt-rag-ingestion copilot-instructions.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 4d 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.

.github/copilot-instructions.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository development and release instructions

Read AGENTS.md and every scoped instruction that applies to changed files. Executable configuration and current implementation take precedence over examples in prose.

Branching

This repository uses:

develop for ongoing development;
main for stable released versions.

Unless a maintainer explicitly authorizes an exception:

Start implementation work from develop.
Use feature/<short-description> for feature branches.
Target feature pull requests to develop, never main.
Use release/x.y.z branches created from develop.
Target release pull requests to main.

Do not mix new feature work into release branches. A maintainer-authorized one-off branch or pull-request target exception applies only to that task and does not change repository policy.

Use clear conventional commit subjects such as:

feat: add document format support
fix: preserve index authorization metadata
docs: document ingestion configuration
chore: prepare release 2.6.0

Versioning

Follow semantic versioning:

PATCH: compatible bug fixes and small compatible improvements.
MINOR: backward-compatible features.
MAJOR: breaking changes.

For release 2.6.0, keep these forms aligned:

Surface	Value
Branch	`release/2.6.0`
Root `VERSION`	`2.6.0`
Changelog heading	`## [v2.6.0] - YYYY-MM-DD`
Git tag and GitHub Release title	`v2.6.0`

Never add v to VERSION or a release branch name. Feature work must not preemptively change VERSION.

The GitHub Release title must be exactly the tag, with no product or service prefix: use v2.6.0, never GPT-RAG Ingestion v2.6.0 or gpt-rag-ingestion v2.6.0.

Changelog lifecycle

CHANGELOG.md follows Keep a Changelog and uses Added, Changed, Fixed, and Removed when applicable.

On develop:

maintain exactly one ## [Unreleased] section;
add every user-, operator-, deployment-, contract-, or release-relevant change under it;
do not create a future numbered release section.

Read the full file on GitHub · 124 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.

4d ago Changed · +3 lines · +58 tokens per session 0340f9ba1b19
8d ago First seen · 121 lines · 910 tokens per session scan A 0b5e73a1eb4b

Subscribe to this mod's changes

gpt-rag-ingestion copilot-instructions.md is an instructions file published in the GitHub repository Azure/gpt-rag-ingestion (189 stars, last pushed today), licensed MIT. It adds 968 tokens to every session, about $0.0048 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.

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

gpt-rag-ingestion: Instructions file for GitHub Copilot