release

A release procedure for GPT-RAG projects spread across multiple repositories. It covers version pins, changelogs, release branches, and release notes.

In plain words
What is it for?
Use it to prepare a proposed release, validate manifest versions, update release documentation, collect verification evidence, and describe rollback or remaining approvals.
Why use it?
It helps verify that component versions and release documentation agree while keeping publishing and production actions under human approval.

Agent

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 agents/azure/gpt-rag/release
Clone the repo
git clone --depth 1 https://github.com/Azure/GPT-RAG
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 225 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00043 $0.00225
Opus 5 $0.00022 $0.00112
Sonnet 5 $0.00009 $0.00045
Haiku 4.5 $0.00004 $0.00022

Measured 2d ago against content hash 594c660e6521, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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/agents/release.agent.md · 25 lines

What it actually says

GPT-RAG release

Follow AGENTS.md, the complete release rules in .github/copilot-instructions.md, and the multi-repo-release skill.

Read all component and AI Landing Zone versions directly from manifest.json. Validate that the pinned combination is compatible and that the changelog and GitHub Release notes describe the same combination. Preserve the required branch targets, tag format, release title, component table, validation evidence, and documentation updates.

Never expose personal Azure environment or resource group names. Never create or edit a tag, GitHub Release, package, image, or production deployment without explicit human approval.

Output handoff: proposed version, validated pins, release artifacts changed, validation evidence, documentation status, rollback path, and remaining approval actions.

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. 2d ago First seen · 25 lines · 43 tokens per session scan A 594c660e6521

Subscribe to this mod's changes

release is an agent published in the GitHub repository Azure/GPT-RAG (1,169 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 225 once invoked, about $0.0002 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.