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/adogit 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/ado)<a href="https://agentmods.dev/commands/microsoft/skills/ado"><img src="https://agentmods.dev/badge/commands/microsoft/skills/ado.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 | $0.00039 | $0.02232 |
| Opus 5 | $0.00019 | $0.01116 |
| Sonnet 5 | $0.00008 | $0.00446 |
| Haiku 4.5 | $0.00004 | $0.00223 |
Grade A, and why
ado 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Wiki: Azure DevOps Wiki Export
You are a Technical Documentation Engineer. Generate a Node.js build script that converts the VitePress wiki output into Azure DevOps (ADO) Wiki-compatible markdown.
Source Repository Resolution (MUST DO FIRST)
Before generating the build script, resolve the source repository context:
- Check for git remote: Run
git remote get-url origin - Ask the user: "Is this a local-only repository, or do you have a source repository URL?"
- Remote URL → store as
REPO_URL, preserve linked citations in converted output - Local → preserve local citations as-is
- Remote URL → store as
- Do NOT proceed until resolved
Context
Azure DevOps Wikis use a markdown dialect that differs from GFM/VitePress in critical ways. This command creates a preprocessing script that reads the generated wiki .md files, applies targeted transformations, and writes ADO-compatible copies to dist/ado-wiki/.
Source files are NEVER modified. Only transformed copies are written to the output directory.
Process
Step 1: Scan the Wiki Directory
Locate the generated wiki output (typically wiki/ or the VitePress source directory). Scan for incompatibilities:
# Count mermaid code fence blocks
grep -rc '```mermaid' --include="*.md" wiki/ | grep -v ':0$'
# Find flowchart keyword usage
grep -rn '^\s*flowchart ' --include="*.md" wiki/
# Find <br> tags in mermaid labels
grep -rn '<br>' --include="*.md" wiki/ | head -20
# Count YAML front matter files
for f in $(find wiki/ -name "*.md"); do
head -1 "$f" | grep -q '^---$' && echo "FRONT MATTER: $f"
done
# Find parent-relative links
grep -rn '](\.\./' --include="*.md" wiki/ | wc -l
# Find VitePress container directives
grep -rn '^:::' --include="*.md" wiki/ | grep -v mermaid
Report the scan results before proceeding.
Step 2: Generate the Build Script
Create scripts/build-ado-wiki.js — a Node.js ESM script with zero external dependencies (only node:fs/promises, node:path, node:url).
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 · 207 lines · 39 tokens per session scan A 9fb17a5bcc02
ado is a command published in the GitHub repository microsoft/skills (2,989 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 2,232 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.
add-seo
Add comprehensive SEO to a page using Next.js 15 Metadata API.