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.
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.
curl -O https://raw.githubusercontent.com/Azure/gpt-rag-ingestion/main/.github/skills/release/SKILL.mdgit clone --depth 1 https://github.com/Azure/gpt-rag-ingestionWrote 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-ingestion/release)<a href="https://agentmods.dev/skills/azure/gpt-rag-ingestion/release"><img src="https://agentmods.dev/badge/skills/azure/gpt-rag-ingestion/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-ingestion/release"><img src="https://agentmods.dev/badge/skills/azure/gpt-rag-ingestion/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 | $0.00057 | $0.01689 |
| Opus 5 | $0.00028 | $0.00844 |
| Sonnet 5 | $0.00011 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Prepare releases for this repository without publishing artifacts or changing Azure resources until a human explicitly approves the publication step.
Non-negotiable rules
- Treat
developas the release source andmainas the stable release target. - Create
release/X.Y.Zfrom an up-to-dateorigin/develop; never include avprefix in the branch name or rootVERSIONfile. - Open the release pull request from
release/X.Y.Ztomain. - Use Semantic Versioning (
MAJOR.MINOR.PATCH) and reject malformed, prerelease, or build-metadata versions unless the human request explicitly defines a supported policy for them. - Use exactly
vX.Y.Zfor both the Git tag and GitHub release title. - Keep the release branch,
VERSION, changelog heading, tag, release title, and release target commit consistent. - Run the repository's existing validation before requesting publication approval. Do not invent a passing result or skip a failing check.
- Do not add or depend on organization-only manifests, central release catalogs, private automation, or data that is absent from this repository.
- Do not create a release custom agent. This skill owns the reusable release guidance.
- Never create or mutate Azure resources as part of release preparation.
1. Discover the authoritative released version
Start from a clean worktree and refresh remote state:
git fetch origin develop main --tags --prune
git status --short
git tag --list "v*" --sort=-v:refname
gh release list --limit 100
Read every tracked version source that exists, including:
- root
VERSION; - versioned headings in
CHANGELOG.md; - package manifests or generated version modules found in the repository;
- published Git tags matching
vX.Y.Z; - published GitHub releases and their target commits.
The highest valid published vX.Y.Z tag and GitHub release are the
authoritative released baseline. They must describe the same version and
commit. Repository version files on develop must agree with the latest
released baseline unless the repository documents a deliberate post-release
version update. If tags, releases, version files, or changelog entries
disagree, stop release preparation and reconcile the discrepancy before
selecting the next version. Do not infer a version from branch names, commit
counts, dates, image tags, or private deployment state.
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.
- 9d ago First seen · 181 lines · 57 tokens per session scan A d87fcddb2ae9
release is a skill published in the GitHub repository Azure/gpt-rag-ingestion (189 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,689 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
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
updater_guide
Guidance for checking for and installing Row-Bot updates.