gpt-rag-ingestion release-documentation.instructions.md

gpt-rag-ingestion release-documentation.instructions.md is an instructions file for GitHub Copilot from Azure/gpt-rag-ingestion. It costs 219 tokens per session, scanned A, original, MIT.

Release documentation instructions for a service that prepares documents for Azure AI Search, Microsoft's search service for business data. They explain how to keep version information, changelogs, and user guidance accurate.

In plain words
What is it for?
Use them when changing release notes, README guidance, or shared product documentation for the document-ingestion service.
Why use it?
They prevent release notes and documentation from drifting away from the code. They also reduce the risk of exposing private Azure environment details.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

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

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 instructions/azure/gpt-rag-ingestion/release-documentation
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.

agentmods badge for gpt-rag-ingestion release-documentation.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/azure/gpt-rag-ingestion/release-documentation.svg)](https://agentmods.dev/instructions/azure/gpt-rag-ingestion/release-documentation)
Your own site
<a href="https://agentmods.dev/instructions/azure/gpt-rag-ingestion/release-documentation"><img src="https://agentmods.dev/badge/instructions/azure/gpt-rag-ingestion/release-documentation.svg" alt="Measured on agentmods" height="20"></a>
Per session 219 This file is loaded in full into every session.
When invoked 219 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 5.1 $0.00219 $0.00219
Opus 5 $0.00110 $0.00110
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 6d ago against content hash 8f4881da5794, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gpt-rag-ingestion release-documentation.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 6d 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/instructions/release-documentation.instructions.md · 22 lines

What it actually says

Release metadata and documentation

  • Follow .github/copilot-instructions.md completely.
  • On feature work, do not change VERSION.
  • On develop, stage changes under exactly one ## [Unreleased].
  • On release/x.y.z, set VERSION to x.y.z and convert Unreleased to ## [vX.Y.Z] - YYYY-MM-DD.
  • Never add Unreleased to a release branch or main.
  • Changelog entries use a bold descriptive title and explain behavior and impact with relevant technical context.
  • Keep ingestion-specific service and audit guidance in README.md aligned with code and contracts.
  • Coordinate cross-component user/operator documentation on the docs branch of Azure/GPT-RAG.
  • Never publish private Azure environment or resource-group names.
  • Load service-release for release work and documentation-consistency for user- or operator-visible changes.
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. 6d ago First seen · 22 lines · 219 tokens per session scan A 8f4881da5794

Subscribe to this mod's changes

gpt-rag-ingestion release-documentation.instructions.md is an instructions file published in the GitHub repository Azure/gpt-rag-ingestion (189 stars, last pushed 2d ago), licensed MIT. It adds 219 tokens to every session, about $0.0011 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.