Azure Search OpenAI Demo is a sample chat application that answers questions about a user's documents by retrieving relevant content with Azure AI Search and generating responses with Azure OpenAI models. It is intended for developers learning to build retrieval-augmented generation applications on Azure, and its catalogue entries provide agents and instructions for working with the sample.
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.
git clone --depth 1 https://github.com/Azure-Samples/azure-search-openai-demoWrote 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/agents/azure-samples/azure-search-openai-demo/fixer)<a href="https://agentmods.dev/agents/azure-samples/azure-search-openai-demo/fixer"><img src="https://agentmods.dev/badge/agents/azure-samples/azure-search-openai-demo/fixer/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/agents/azure-samples/azure-search-openai-demo/fixer"><img src="https://agentmods.dev/badge/agents/azure-samples/azure-search-openai-demo/fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00006 | $0.00660 |
| Opus 5 | $0.00003 | $0.00330 |
| Sonnet 5 | $0.00001 | $0.00132 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
fixer 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixer Mode Instructions
You are in fixer mode. When given an issue to fix, follow these steps:
- Gather context: Read error messages/stack traces/related code. If the issue is a GitHub issue link, use 'get_issue' and 'get_issue_comments' tools to fetch the issue and comments.
- Make targeted fix: Make minimal changes to fix the issue. Do not fix any issues that weren't identified. If any other issues pop up, note them as potential issues to be fixed later.
- Verify fix: Test the application to ensure the fix works as intended and doesn't introduce new issues. For a backend change, add a new test in the tests folder and run the tests with VS Code "runTests" tool. RUN all the tests using that tool, not just the tests you added. Try to add tests to existing test files when possible, like test_app.py. DO NOT run the
pytestcommand directly or create a task to run tests, ONLY use "runTests" tool. For a frontend change, use the Playwright server to manually verify or update e2e.py tests.
Local server setup
You MUST check task output readiness before debugging, testing, or declaring work complete.
- Start the app: Run the "Development" compound task (which runs both frontend and backend tasks) and check readiness from task output. Both must be in ready state:
- Frontend task: "Frontend: npm run dev"
- Backend task: "Backend: quart run"
- Investigate and fix errors shown in the corresponding task terminal before proceeding. You may sometimes see an error with /auth_setup in frontend task, that's due to the backend server taking longer to startup, and can be ignored.
- Both of the tasks provide hot reloading behavior:
- Frontend: Vite provides HMR; changes in the frontend are picked up automatically without restarting the task.
- Backend: Quart was started with --reload; Python changes trigger an automatic restart.
- If watchers seem stuck or output stops updating, stop the tasks and run the "Development" task again.
- To interact with a running application, use the Playwright MCP server. If testing login, you will need to navigate to 'localhost' instead of '127.0.0.1' since that's the URL allowed by the Entra application.
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.
- 11d ago First seen · 41 lines · 6 tokens per session scan A 944f05305be9
fixer is an agent published in the GitHub repository Azure-Samples/azure-search-openai-demo (7,758 stars, last pushed 8d ago), licensed MIT. It adds 6 tokens to every session and 660 once invoked, about $0.0000 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 agents, from other repositories
architecture
Analyzes GPT-RAG boundaries, contracts, security, deployment topology, and trade-offs. Use for structural or hard-to-reverse changes; do not use for local implementation work with settled requirements.
release
Prepares and validates GPT-RAG multi-repository releases. Use for manifest pins, changelog entries, release branches, and release notes; do not use for feature implementation or publish without explicit human approval.
implementation
Implements, tests, and documents scoped GPT-RAG changes after requirements are clear. Do not use to decide broad architecture or publish releases.
cs-guardian
Customer success partner for account health, churn risk, renewals, escalations, and QBRs. Use to score an account, diagnose churn, prep a renewal or QBR, or write an escalation brief. Computes the weighted health score programmatically.
Codebase-Explorer
Help engineers learn about the codebase and programming concepts of this project.
app-repair
Repairs a live Mewbo App after a pipeline failure or user feedback — fixes data, frontend, or schedule and ships a new version.