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/buildgit 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/build)<a href="https://agentmods.dev/commands/microsoft/skills/build"><img src="https://agentmods.dev/badge/commands/microsoft/skills/build.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 | $0.00024 | $0.05846 |
| Opus 5 | $0.00012 | $0.02923 |
| Sonnet 5 | $0.00005 | $0.01169 |
| Haiku 4.5 | $0.00002 | $0.00585 |
Grade A, and why
build 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 — 648 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Wiki: Build VitePress Site
Package the generated wiki markdown files into a complete VitePress site with a Daytona-inspired dark theme, dark-mode Mermaid diagrams, and click-to-zoom for diagrams and images.
Prerequisites
The wiki markdown files should already exist (from /deep-wiki:generate or manual creation). This command scaffolds the VitePress project around them.
Step 1: Scaffold VitePress Project
Create a wiki/ directory with this structure:
wiki/
├── package.json
├── .gitignore
├── AGENTS.md # Agent instructions for wiki folder
├── CLAUDE.md # Companion pointer to AGENTS.md
├── index.md # Wiki home page (NOT a placeholder — see below)
├── llms.txt # LLM-friendly links + descriptions
├── llms-full.txt # LLM-friendly full inlined content
├── onboarding/ # Audience-tailored onboarding guides
│ ├── index.md # Onboarding hub with guide selector
│ ├── contributor-guide.md # For new contributors (assumes Python/JS)
│ ├── staff-engineer-guide.md # For staff/principal engineers
│ ├── executive-guide.md # For VP/director-level leaders
│ └── product-manager-guide.md # For product managers
├── {NN}-{section-name}/ # Numbered section folders
│ ├── {page-name}.md
│ └── ...
├── .vitepress/
│ ├── config.mts # Full VitePress config
│ ├── public/
│ │ ├── logo.svg # Brand logo
│ │ ├── llms.txt # Served at /llms.txt on deployed site
│ │ └── llms-full.txt # Served at /llms-full.txt on deployed site
│ └── theme/
│ ├── index.ts # Theme setup (zoom handlers)
│ └── custom.css # Complete dark theme + Mermaid + zoom CSS
index.md — Wiki Landing Page (CRITICAL)
The index.md MUST be a developer-focused wiki home page — NOT a marketing landing page. No hero: frontmatter blocks, no taglines, no call-to-action buttons. This is a technical wiki, not a product page.
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 · 648 lines · 24 tokens per session scan A 26dbd05155e5
build is a command published in the GitHub repository microsoft/skills (2,992 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 5,846 once invoked, about $0.0001 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.