microsoft/skills is a collection of skills, custom agents, AGENTS.md templates, plugins, hooks, commands, and MCP configurations that give AI coding agents context for Azure SDK and Microsoft AI Foundry development. Developers use it to install selected domain-specific guidance into coding-agent environments. The catalogue entries are the repository’s own agent resources and supporting configurations.
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.
npx agentmods add commands/microsoft/skills/agentsgit clone --depth 1 https://github.com/microsoft/skillsWrote 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/commands/microsoft/skills/agents)<a href="https://agentmods.dev/commands/microsoft/skills/agents"><img src="https://agentmods.dev/badge/commands/microsoft/skills/agents.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.02106 |
| Opus 5 | $0.00016 | $0.01053 |
| Sonnet 5 | $0.00007 | $0.00421 |
| Haiku 4.5 | $0.00003 | $0.00211 |
Grade A, and why
agents 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 yesterday.
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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Wiki: Generate AGENTS.md Files
You are a Technical Documentation Architect specializing in coding agent instructions. Generate tailored AGENTS.md files for pertinent folders in this repository.
What is AGENTS.md
AGENTS.md complements README.md. While README is for human contributors, AGENTS.md provides the extra context coding agents need: build commands, test instructions, code conventions, and boundaries. It's a standard, predictable file that any coding agent can find and use.
AGENTS.md ≠ Agent Personas. This is NOT an agent persona file (like .github/agents/*.agent.md). AGENTS.md is project context — the instructions you'd give a new teammate.
⚠️ CRITICAL: Only Generate If Missing
NEVER overwrite an existing AGENTS.md file. For every folder:
- Check if
AGENTS.mdexists (case-sensitive) - If YES → skip, report: "✅ AGENTS.md already exists in [folder] — skipping"
- If NO → generate a new one
This is NON-NEGOTIABLE. Existing AGENTS.md files may have been carefully hand-crafted.
Process
Step 1: Identify Pertinent Folders
Scan the repository and identify folders that should have an AGENTS.md:
Always include:
- Repository root (
./)
Include if they exist:
tests/ortest/— test suitessrc/— source code rootlib/— library codeapp/orapps/*/— application codeapi/— API layerpackages/*/— monorepo packagesservices/*/— microservices
Include if they have their own build system:
- Any folder with
package.json,pyproject.toml,Cargo.toml,*.csproj,go.mod,Makefile
Skip:
node_modules/,dist/,build/,.git/,vendor/,__pycache__/- Generated output directories
- Folders with fewer than 3 source files (unless they have their own package config)
Step 2: Analyze Each Folder
For each pertinent folder, gather:
- Language & Framework — What language(s), what frameworks, what versions
- Build Commands — Read
package.jsonscripts,Makefiletargets,pyproject.tomlscripts,Cargo.toml, CI configs - Test Commands — How to run tests, test framework, how to run a single test
- Entry Points — Main files, index files, app entry points
- Conventions — Look at existing code for naming patterns, import styles, file organization
- CI/CD — Check
.github/workflows/,Jenkinsfile,.gitlab-ci.ymlfor commands - Existing Documentation — Read
README.mdin the folder (don't duplicate it — complement it)
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.
- yesterday First seen · 219 lines · 33 tokens per session scan A d1a93cdc00db
agents is a command published in the GitHub repository microsoft/skills (2,989 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 2,106 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 2026-09-03.
Other commands, from other repositories
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
debug
You are acting as a Debug Specialist with expertise in.
audit-security
Perform comprehensive security audit of the current project.
add-database-railway
Set up PostgreSQL database with Prisma ORM and complete data layer.
setup-monitoring-railway
Configure comprehensive monitoring for Railway deployment.
review-security
Perform comprehensive security audit using code-review-agent and security-production-agent. Scan for OWASP Top 10 vulnerabilities: SQL injection, XSS, CSRF, insecure authentication, broken access control, security misconfiguration, sensitive data exposure, insufficient logging, insecure deserialization, and vulnerable…