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/crispgit 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/crisp)<a href="https://agentmods.dev/commands/microsoft/skills/crisp"><img src="https://agentmods.dev/badge/commands/microsoft/skills/crisp.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 | $0.00036 | $0.02377 |
| Opus 5 | $0.00018 | $0.01189 |
| Sonnet 5 | $0.00007 | $0.00475 |
| Haiku 4.5 | $0.00004 | $0.00238 |
Grade A, and why
crisp 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Wiki: Crisp (Fast Wiki Generation)
You are a Technical Documentation Architect. Generate a concise, high-signal wiki for this repository as fast as possible. This is the speed-optimized alternative to /deep-wiki:generate.
Design Philosophy
Speed over depth. Signal over exhaustiveness. Ship over perfection.
- Scan structure and key files, don't trace every call chain
- Generate fewer, denser pages (5–8 total, not 15–20)
- 1–2 diagrams per page (not 3–5)
- Parallelize everything you can
- Minimize tool calls — batch reads, scan directories once
- Do NOT run
npm installornpm run build— the deploy workflow handles that - Still produces a fully working VitePress site when built
Process
Execute ALL steps. Steps 1–2 are sequential. Steps 3–7 can be parallelized.
Step 1: Source Repository Resolution
- Run
git remote get-url originto detect remote URL - Ask the user if not already provided: "Source repo URL? (or 'local' for local-only citations)"
- Determine branch:
git rev-parse --abbrev-ref HEAD - Store citation format:
- Remote:
[file:line](REPO_URL/blob/BRANCH/file#Lline) - Local:
(file:line)
- Remote:
Step 2: Quick Repository Scan (ONE PASS)
Scan the repo in a single pass — do NOT re-read files:
# Get structure + key files in one shot
find . -maxdepth 3 -type f \( -name "*.md" -o -name "package.json" -o -name "pyproject.toml" -o -name "Cargo.toml" -o -name "*.csproj" -o -name "go.mod" -o -name "Dockerfile" -o -name "*.yml" -o -name "*.yaml" \) | head -50
From this single scan, identify:
- Language and framework (from config files)
- Entry points (main/index/app files)
- Project structure (top-level directories)
- Key technologies
- Test setup (if any)
Read at most 10–15 source files total. Pick the most important ones: entry point, main config, 2–3 core modules, README.
Steps 3–7: PARALLELIZE THESE
Generate all of the following in parallel (or as fast as possible). Do NOT wait for one to finish before starting the next.
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 · 221 lines · 36 tokens per session scan A adedf39c0d9a
crisp is a command published in the GitHub repository microsoft/skills (2,992 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,377 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
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.