GPT-RAG is an Azure solution accelerator for building agentic retrieval-augmented generation systems, where agents use connected organizational sources to ground their answers. It is for organizations deploying secure RAG applications with Microsoft Foundry, Microsoft Agent Framework, and Azure infrastructure. The catalogue add-ons provide agents, skills, and instructions for deploying and working with the accelerator.
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.
npx skills add Azure/GPT-RAG --skill multi-repo-releasegit clone --depth 1 https://github.com/Azure/GPT-RAGWrote 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/skills/azure/gpt-rag/multi-repo-release)<a href="https://agentmods.dev/skills/azure/gpt-rag/multi-repo-release"><img src="https://agentmods.dev/badge/skills/azure/gpt-rag/multi-repo-release/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/skills/azure/gpt-rag/multi-repo-release"><img src="https://agentmods.dev/badge/skills/azure/gpt-rag/multi-repo-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00451 |
| Opus 5 | $0.00028 | $0.00226 |
| Sonnet 5 | $0.00011 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
multi-repo-release 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.
What it actually says
GPT-RAG multi-repository release
Read .github/copilot-instructions.md completely before changing a release
artifact. Its branching, versioning, changelog, and release-note requirements
are authoritative.
- Determine the intended semantic version and create the release branch from
developusingrelease/x.y.z. - Update
manifest.jsontagtovX.Y.Zand verify it matches the release branch version, changelog heading, Git tag, and GitHub Release title. - Read every runtime component tag from
manifest.jsoncomponents[]and the infrastructure tag fromailz_tag; never copy a previous version table. - Require the AI Landing Zone pins to agree:
manifest.jsonailz_tag, the.gitmodulesinfra.branch, and the recordedinfra/submodule gitlink must identify the same validated release commit. - Confirm that the exact pinned combination was validated and record the relevant commands and Azure deployment mode without private environment or resource group names.
- Replace
[Unreleased]with## [vX.Y.Z] - YYYY-MM-DDfor the release. - Keep
CHANGELOG.mdand GitHub Release notes consistent, including the full required component version table. - Use exactly
vX.Y.Zfor both the tag and GitHub Release title. - Target the release pull request to
main. - Re-fetch published release notes and verify headings, lists, tables, and the
absence of private
gptrag-*andrg-gptrag-*validation names.
Do not publish a tag, release, package, image, or production deployment without explicit human approval. Report incompatible pins, missing validation, or documentation drift as blockers rather than filling gaps by assumption.
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.
- 6d ago Changed · +13 tokens per session 1a3b6edb4a4e
- 10d ago First seen · 35 lines · 43 tokens per session scan A f838f912669c
multi-repo-release is a skill published in the GitHub repository Azure/GPT-RAG (1,176 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 451 once invoked, about $0.0003 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 skills, from other repositories
bootstrap-realtime-eval
Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtimeevals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval…
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
update-changelog
Update the CHANGELOG.md files of C# projects. Parameters: csroot C# SDK repository root.
day0-release
Deterministic end-to-end driver for day-0 quantized-checkpoint releases — chains PTQ → evaluation → comparison with enforced gates between stages (the evaluation stage deploys the checkpoint itself), and returns a publish decision (ACCEPT / REGRESSION / ANOMALOUS / INFEASIBLE). Use when the user asks to "release a…
azure-search-documents-py
Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets. Triggers: "azure-search-documents", "SearchClient", "SearchIndexClient", "vector search", "hybrid search", "semantic search".
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…