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/llmsgit 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/llms)<a href="https://agentmods.dev/commands/microsoft/skills/llms"><img src="https://agentmods.dev/badge/commands/microsoft/skills/llms.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 | $0.00025 | $0.02126 |
| Opus 5 | $0.00013 | $0.01063 |
| Sonnet 5 | $0.00005 | $0.00425 |
| Haiku 4.5 | $0.00003 | $0.00213 |
Grade A, and why
llms 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: Generate llms.txt
You are generating llms.txt and llms-full.txt files that provide LLM-friendly access to the wiki documentation. These follow the llms.txt specification.
Source Repository Resolution (MUST DO FIRST)
Before generating, 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, use linked references:[Title](REPO_URL/blob/BRANCH/path) - Local → use relative paths to wiki files
- Remote URL → store as
- Determine default branch: Run
git rev-parse --abbrev-ref HEAD - Do NOT proceed until resolved
What is llms.txt
llms.txt is a standardized markdown file that helps LLMs quickly understand a project. It provides:
- A concise project summary
- Links to key documentation files with brief descriptions
- Structured sections (Onboarding, Architecture, API, etc.)
Two files are generated:
| File | Purpose | Size |
|---|---|---|
llms.txt |
Links + brief descriptions — fits in small context windows | Small (1-5 KB) |
llms-full.txt |
Full inlined content of all linked pages | Large (50-500 KB) |
Step 1: Gather Project Context
Scan the repository and existing wiki (if generated) to collect:
- Project identity — name, one-sentence description, primary language, key technologies
- Wiki pages — scan
wiki/directory for all generated.mdfiles - Onboarding guides — check for
onboarding/folder with audience-tailored guides - README — extract the core project description
- Key entry points — main files, API surface, configuration
Step 2: Generate llms.txt
Create wiki/llms.txt following the llms.txt spec format:
# {Project Name}
> {One-paragraph summary: what it does, who it's for, key technologies. Dense and informative.}
{2-3 paragraphs of important context: architectural philosophy, key constraints, what makes this project different. Include things an LLM needs to know to give accurate answers about this project.}
## Onboarding
- [{Contributor Guide}](./onboarding/contributor-guide.md): Step-by-step guide for new contributors — environment setup, first task, testing, and coding conventions
- [{Staff Engineer Guide}](./onboarding/staff-engineer-guide.md): Architectural deep-dive for senior engineers — design decisions, domain model, component types, and failure modes
- [{Executive Guide}](./onboarding/executive-guide.md): Capability overview for engineering leaders — risk assessment, technology investment, and scaling model
- [{Product Manager Guide}](./onboarding/product-manager-guide.md): Feature-focused guide for PMs — user journeys, capabilities, limitations, and data/privacy
## Architecture
- [{Architecture Overview}](./02-architecture/overview.md): System architecture, component boundaries, and deployment topology
- [{Data Model}](./02-architecture/data-model.md): Core entities, relationships, and data invariants
- [{API Reference}](./02-architecture/api-reference.md): Endpoints, authentication, and wire format
## Getting Started
- [{Setup Guide}](./01-getting-started/setup.md): Prerequisites, installation, and first run
- [{Configuration}](./01-getting-started/configuration.md): Environment variables, feature flags, and config files
## Deep Dive
- [{Component Name}](./03-deep-dive/component.md): Description of component purpose and scope
- ...additional pages...
## Optional
- [{Changelog}](./changelog.md): Recent changes and version history
- [{Contributing}](./contributing.md): How to contribute to the project
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 · 25 tokens per session scan A 52dbc9ab2789
llms is a command published in the GitHub repository microsoft/skills (2,989 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 2,126 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.