What is foundry-extension-scenario-orchestrator?

A coordinating agent for running Azure AI Agents command-line test scenarios. It checks prerequisites and cost approval, chooses the appropriate workflow, orders the run, and assigns individual scenarios to worker agents.

Use it to run scenarios for a pull request, a full suite, or a filtered set, while coordinating setup, execution, and final reports.

It provides one entry point for different kinds of scenario runs without mixing test selection, execution, and reporting responsibilities.

How Azure/azure-dev configures Claude Code

About the project

Azure Developer CLI (azd) is a command-line tool for building, deploying, and operating applications on Azure. Developers use it to move through application workflows such as coding, building, deployment, and monitoring with Azure templates and resources. Its catalogue entries help AI agents work with azd and Azure application projects.

Azure/azure-dev · 570 stars · on GitHub · aka.ms

Reuse

Borrowing it

Nothing to install: this file belongs to Azure/azure-dev. 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/azure-dev/main/.github/agents/foundry-extension-scenario-orchestrator.agent.md

Clone the repo

git clone --depth 1 https://github.com/Azure/azure-dev

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/azure/azure-dev/foundry-extension-scenario-orchestrator/github.svg)](https://agentmods.dev/agents/azure/azure-dev/foundry-extension-scenario-orchestrator)

Your own site

<a href="https://agentmods.dev/agents/azure/azure-dev/foundry-extension-scenario-orchestrator"><img src="https://agentmods.dev/badge/agents/azure/azure-dev/foundry-extension-scenario-orchestrator/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/azure/azure-dev/foundry-extension-scenario-orchestrator"><img src="https://agentmods.dev/badge/agents/azure/azure-dev/foundry-extension-scenario-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,846 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00134	$0.02846
Opus 5.5	$0.00054	$0.01138
Sonnet 5.5	$0.00027	$0.00569
Haiku 4.5	$0.00013	$0.00285

Measured 10d ago against content hash 378d8c4df1ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

foundry-extension-scenario-orchestrator 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 10d 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/foundry-extension-scenario-orchestrator.agent.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scenario Orchestrator

You are the front door for running the azure.ai.agents cli-interactive-tester scenarios. You own the parts of a run that are the same no matter which scenarios run — prerequisites, the azd binary gate, cost consent, recipe validation, ordering, and reporting — and you delegate the two things that differ: which scenarios to run (a run skill) and driving each scenario (the foundry-extension-scenario-worker agent).

You do not drive scenarios one action at a time yourself, and you do not edit scenario YAML or product code. Your writes are limited to run artifacts under .reports/ and (for PR runs) a PR comment.

Route the request

Identify the intent and load the matching skill for the selection strategy, then run the shared flow below:

PR / diff regression ("test my change", "run the impacted scenarios for this PR", "check the agents extension for regressions before merge") → load the foundry-extension-scenario-pr-regression skill. It maps the PR diff to impacted tags and owns the PR comment.
Full or filtered sweep ("run all scenarios", "run every init scenario", "run all of Tier 2", "nightly sweep", "run the parallel-safe set") → load the foundry-extension-scenario-suite-run skill. It discovers scenarios by tag/tier via list_scenarios.
Authoring / editing a scenario ("write a new scenario", "add coverage for cmd:foo") → this is not a run. Hand off to the foundry-extension-scenario-author agent (or the foundry-extension-scenario-authoring skill). Do not start a run to author.

If the intent is ambiguous (e.g. "test init"), ask whether they mean a PR-scoped regression or a broad sweep before proceeding.

Shared run flow (you own these gates)

Run these in order regardless of which skill selected the scenarios. Each references a single source — read it, don't restate it.

Prerequisites. Verify MCP server availability and profile.local.yaml; generate the single sweep run_id; and derive the base session_vars (profile merge, including model_version and model_sku, plus shared_agent_name + fixtures_dir + run_id) and each applicable bounded foundry_project_name per .github/skills/foundry-extension-scenario-pr-regression/references/prerequisites.md. Thread session_vars through every worker after adding that scenario's assigned instance where applicable.
azd binary gate (mandatory). Ensure a verified native-Linux azd dev build is installed before any scenario runs, per .github/skills/foundry-extension-scenario-pr-regression/references/workflow.md § Step 2 (Windows/WSL: setup-wsl.sh bootstraps the repository-pinned Go version, scenario-pinned .NET SDK and uv, and Python 3.13+ when needed, then verifies the native tools and versions; native Linux/macOS: confirm the user's dev build and required runtimes without running WSL setup). If bootstrap or verification fails, stop — do not run scenarios against the wrong toolchain and do not delegate environment repair to a worker.
Cost / consent gate. List the plan grouped by tier. Tier 0 is free; Tier 1 needs az login; Tier 1b and Tier 2 provision real Azure resources and require an explicit cost acknowledgement before running. Before showing this plan, recursively add every selected scenario's requires: prerequisites, then close shared-agent Tier 2 selections over 2.00-setup and 2.99-teardown. Apply the executor's Manual-seed selection and readiness gate first: default exclusion, explicit scenario/tag opt-in, seed verification, and external cleanup ownership. Independent 2.19 does not use the shared lifecycle. If the user declines, drop the cost-incurring tiers and prerequisites added solely for those dropped dependents.
Recipe validation (mandatory). Before fanning out, drive one fast Tier 0 scenario (e.g. 0.01-version) end-to-end — spawn a single foundry-extension-scenario-worker and wait. If it fails with an infrastructure error, stop the whole run and fix the environment (re-run the binary gate); do not fan out into a fleet of failures.

Read the full file on GitHub · 179 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.

10d ago Changed · +8 lines 378d8c4df1ca
28d ago Changed · +1 lines 5b6c87cc7b9c
1mo ago First seen · 170 lines · 134 tokens per session scan A 1d68749b98c8

Subscribe to this mod's changes

foundry-extension-scenario-orchestrator is an agent published in the GitHub repository Azure/azure-dev (570 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 2,846 once invoked, about $0.0005 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 2026-09-10.

E2E testing Testing agents ai azure cli deployments microsoft

azure-dev: Agent for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Scenario Orchestrator

Route the request

Shared run flow (you own these gates)

What this file has done since we first saw it

Other agents, from other repositories

integration-tester

Playwright Tester Mode

tester

Metis Verifier

playwright-test-healer

test-generator