AGENTS.md@testsA

AGENTS.md@tests from microsoft/github-copilot-for-azure is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add microsoft/github-copilot-for-azure/tests/AGENTS.md@git:20260923.0403a05

Pins git:20260923.0403a05 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
microsoft/github-copilot-for-azure
Path
tests/AGENTS.md
Versions recorded
6
Latest version
git:20260923.0403a05, committed Sep 23, 2026
First version recorded
Mar 19, 2026
Size
6,712 bytes
Repository stars
259
License
a license file GitHub does not identify

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Skills Testing Guide

> **For AI Agents**: This document provides patterns and conventions for creating and maintaining tests for azure-skills plugin. When asked to "scaffold tests" for a skill, follow the instructions below.

## Scaffolding Tests for a Skill

When a user asks to scaffold, create, or add tests for a skill, follow these steps:

### Step 1: Read the vally-eval skill

Skills in azure-skills plugin use [vally](https://microsoft.github.io/vally/get-started/) to run integration tests that run prompts against an LLM Agent and evaluate the outcome. The vally-eval skill provides the knowledge on where to add the test code, how to run the tests and where to collect the test results. Combine the instructions in vally-eval skill, the official documentation of vally and the rest of the instructions in this file to learn how to write vally eval suites for azure-skills plugin. 

### Step 2: Read the skill's SKILL.md
Load the file at `plugins/{plugin}/skills/{skill-name}/SKILL.md` to understand:
- The skill's name and description (from frontmatter)
- What the skill does (from content)
- What Azure services/tools it references
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add microsoft/github-copilot-for-azure/tests/AGENTS.md@sha256:f341cd28c5eef647

The line at the top of this page pins the label git:20260923.0403a05, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rwmaa2btqxahrisz.svg)](https://markdownregistry.com/a/art_rwmaa2btqxahrisz)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Mar 19, 2026 and Sep 23, 2026, about one every 38 days.

versioncommittedcommitsizeaudit
git:20260923.0403a05 latest2026-09-23 0403a05 6,712 BA view · diff
git:20260804.34ec86d2026-08-04 34ec86d 6,660 BA view · diff
git:20260608.275aa182026-06-08 275aa18 6,650 BA view · diff
git:20260527.a581abd2026-05-27 a581abd 6,678 BA view · diff
git:20260518.8456ac42026-05-18 8456ac4 9,841 BA view · diff
git:20260319.08069ef2026-03-19 08069ef 10,643 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (6712 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

microsoft/github-copilot-for-azure · 259 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rwmaa2btqxahrisz
GET https://markdownregistry.com/api/v1/resolve?ref=microsoft/github-copilot-for-azure/tests/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/f341cd28c5eef64723179ea602a441ce8a6668c11741abac73bce41e58f0fb5e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from microsoft/github-copilot-for-azure

analyze-comparison-tests SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/analyze-comparison-tests/SKILL.md · Collects comparison test run artifacts and answers the user's questions based on the trajectories of each run. WHEN TO…
v1.0.0 · audit A · 259 stars
analyze-skill-issues SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/analyze-skill-issues/SKILL.md · Query the integration-test storage account to find why a specific skill's tests are failing. Reads blob-stored test…
v1.0.1 · audit A · 259 stars
analyze-test-run SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/analyze-test-run/SKILL.md · Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues…
v1.0.6 · audit A · 259 stars
file-test-bug SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/file-test-bug/SKILL.md · File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for…
v1.0.0 · audit A · 259 stars
investigate-integration-test SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/investigate-integration-test/SKILL.md · Investigate a failing integration test from a GitHub issue. Downloads logs/artifacts, analyzes the failure, examines…
v1.0.0 · audit A · 259 stars
markdown-token-optimizer SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/markdown-token-optimizer/SKILL.md · Analyzes markdown files for token efficiency. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too…
v1.0.0 · audit A · 259 stars
onboard-plugin SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/onboard-plugin/SKILL.md · Scaffold a new plugin and prepare it for distribution. WHEN: 'create a new plugin', 'scaffold a new plugin'
v1.1.1 · audit A · 259 stars
sensei SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/sensei/SKILL.md · Iteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve…
v1.0.6 · audit A · 259 stars
skill-authoring SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/skill-authoring/SKILL.md · Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new…
v1.0.2 · audit A · 259 stars
skill-reviewer SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/skill-reviewer/SKILL.md · Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo…
v1.0.4 · audit A · 259 stars
vally-eval SKILL.md skill
microsoft/github-copilot-for-azure · .github/skills/vally-eval/SKILL.md · Author, validate, and run Vally evaluation suites for agent skills. TRIGGERS: create eval, write eval, add eval, run…
v1.1.0 · audit A · 259 stars
aks-cost-optimization SKILL.md skill
microsoft/github-copilot-for-azure · plugins/aks-skills/skills/aks-cost-optimization/SKILL.md · Analyze advanced AKS cost efficiency. WHEN: "AKS NAP readiness", "AKS bin packing", "AKS node scaling bottleneck", "AKS…
v0.0.0-placeholder · audit A · 259 stars

Every file in microsoft/github-copilot-for-azure

Other files named AGENTS.md@tests

AGENTS.md@tests AGENTS.md file
metalbear-co/mirrord · tests/AGENTS.md
git:20261028.be6a47a · audit A · 5,401 stars
AGENTS.md@tests AGENTS.md file
homeassistant-ai/ha-mcp · tests/AGENTS.md
git:20261101.7a52f3a · audit B · 5,399 stars
AGENTS.md@tests AGENTS.md file
vercel-labs/fx · tests/AGENTS.md
git:20261102.2c671e1 · audit A · 3,746 stars
AGENTS.md@tests AGENTS.md file
sipyourdrink-ltd/bernstein · tests/AGENTS.md
git:20261024.e491978 · audit A · 1,289 stars
AGENTS.md@tests AGENTS.md file
jasonxudeveloper/nino · tests/AGENTS.md
git:20261103.b8080de · audit A · 652 stars
AGENTS.md@tests AGENTS.md file
izittmarvin/nova-agent · tests/AGENTS.md
git:20260908.e2d0385 · audit A · 168 stars
AGENTS.md@tests AGENTS.md file
ppgranger/token-saver · tests/AGENTS.md
git:20260919.8bd664b · audit A · 162 stars
AGENTS.md@tests AGENTS.md file
damionrashford/rivalsearchmcp · tests/AGENTS.md
git:20260222.c55f9bc · audit A · 134 stars

Browse by kind, by grade A, or by owner.