agentmods.dev

aisearch-openai-rag-audio: Instructions file for Codex

AGENTS.md

aisearch-openai-rag-audio AGENTS.md is an instructions file for Codex, OpenCode from Azure-Samples/aisearch-openai-rag-audio. It costs 3,306 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents working on VoiceRAG, an application for asking questions by voice against a searchable knowledge base. It describes the React frontend, Python backend, Azure services, project layout, and local setup.

In plain words
What is it for?
Use it when developing, running, or deploying the VoiceRAG application.
Why use it?
It gives agents the context needed to work safely across the application’s frontend, backend, and cloud configuration.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is Azure-Samples/aisearch-openai-rag-audio's own configuration. It tells Codex and OpenCode how to work on aisearch-openai-rag-audio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aisearch-openai-rag-audio configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../...

not rated 564repo yesterday A scan 3,306 tokens original MIT
View source ↗ Azure-Samples/aisearch-openai-rag-audio azure.microsoft.com
Reuse

Borrowing it

Nothing to install: this file belongs to Azure-Samples/aisearch-openai-rag-audio. 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-Samples/aisearch-openai-rag-audio/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Azure-Samples/aisearch-openai-rag-audio

Made for: Codex, OpenCode.

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 aisearch-openai-rag-audio AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/azure-samples/aisearch-openai-rag-audio/agents-md/github.svg)](https://agentmods.dev/instructions/azure-samples/aisearch-openai-rag-audio/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/azure-samples/aisearch-openai-rag-audio/agents-md"><img src="https://agentmods.dev/badge/instructions/azure-samples/aisearch-openai-rag-audio/agents-md/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.

agentmods 80×15 button for aisearch-openai-rag-audio AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/azure-samples/aisearch-openai-rag-audio/agents-md"><img src="https://agentmods.dev/badge/instructions/azure-samples/aisearch-openai-rag-audio/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,306 This file is loaded in full into every session.
When invoked 3,306 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03306 $0.03306
Opus 5.5 $0.01322 $0.01322
Sonnet 5.5 $0.00661 $0.00661
Haiku 4.5 $0.00331 $0.00331

Measured 2mo ago against content hash bdbf74f9f169, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aisearch-openai-rag-audio AGENTS.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 2mo 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.

AGENTS.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for Coding Agents

This file contains instructions for developers and automated coding agents working on the VoiceRAG application. It covers code layout, environment setup, testing procedures, and development conventions.

Overview

VoiceRAG is an application pattern demonstrating RAG (Retrieval Augmented Generation) with voice interfaces using Azure AI Search and the GPT-4o Realtime API for Audio. The application enables voice-based interactions with a knowledge base, with audio input processed through the browser and sent to Azure OpenAI's real-time API for responses.

Main technologies:

  • Backend: Python 3.11+ with aiohttp web framework
  • Frontend: React with TypeScript, built with Vite
  • Infrastructure: Azure Bicep templates for Azure Container Apps deployment
  • Key Azure Services: Azure OpenAI (GPT-4o Realtime API), Azure AI Search, Azure Container Apps
  • Deployment: Azure Developer CLI (azd)

Primary entry points:

  • app/backend/app.py - Backend application server (aiohttp)
  • app/frontend/src/main.tsx - Frontend React application
  • scripts/start.sh or scripts/start.ps1 - Development server startup scripts

Code layout

  • app/ - Main application code
    • app/backend/ - Python backend code
      • app/backend/app.py - Main entry point for backend server (aiohttp)
      • app/backend/rtmt.py - Real-time middle tier for Azure OpenAI integration
      • app/backend/ragtools.py - RAG tools for Azure AI Search integration
      • app/backend/setup_intvect.py - Setup script for integrated vectorization
      • app/backend/requirements.txt - Python dependencies
    • app/frontend/ - React TypeScript frontend
      • app/frontend/src/ - Source code for React components
      • app/frontend/src/locales/ - Translation files (en, es, fr, ja)
      • app/frontend/package.json - Node.js dependencies
      • app/frontend/vite.config.ts - Vite build configuration
    • app/Dockerfile - Container image definition for deployment
  • infra/ - Bicep infrastructure-as-code templates
    • infra/main.bicep - Main infrastructure definition
    • infra/main.parameters.json - Template parameters
    • infra/core/ - Reusable Bicep modules
  • scripts/ - Helper scripts for development and deployment
    • scripts/start.sh / scripts/start.ps1 - Start development server
    • scripts/write_env.sh / scripts/write_env.ps1 - Generate .env file from azd
    • scripts/setup_intvect.sh / scripts/setup_intvect.ps1 - Setup integrated vectorization
    • scripts/load_python_env.sh / scripts/load_python_env.ps1 - Create Python virtual environment
  • data/ - Sample data files (Markdown documents)
  • docs/ - Documentation
    • docs/existing_services.md - Connect to existing Azure services
    • docs/customizing_deploy.md - Customize deployment options
    • docs/manual_setup.md - Manual setup instructions
  • .github/workflows/ - GitHub Actions workflows
    • .github/workflows/template-validation.yaml - Template validation workflow
    • .github/workflows/azure-dev.yml - Azure deployment workflow
  • azure.yaml - Azure Developer CLI (azd) configuration
  • pyproject.toml - Python project configuration (ruff linting rules)

Read the full file on GitHub · 380 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.

  1. 2mo ago First seen · 380 lines · 3,306 tokens per session scan A bdbf74f9f169

Subscribe to this mod's changes

aisearch-openai-rag-audio AGENTS.md is an instructions file published in the GitHub repository Azure-Samples/aisearch-openai-rag-audio (564 stars, last pushed yesterday), licensed MIT. It adds 3,306 tokens to every session, about $0.0132 per session on Opus 5.5. 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.

Data and AIFrontendRAG and vectorsReactazuregenerative-aigptlanguage-modelopenai
Related

aisearch-openai-rag-audio AGENTS.md compared with instructions from other repositories

aisearch-openai-rag-audio AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aisearch-openai-rag-audio AGENTS.mdAzure-Samples/aisearch-openai-rag-audioInstructions file564yesterdayMITA3,306Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode