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/changeloggit 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/changelog)<a href="https://agentmods.dev/commands/microsoft/skills/changelog"><img src="https://agentmods.dev/badge/commands/microsoft/skills/changelog.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 5.1 | $0.00014 | $0.00500 |
| Opus 5 | $0.00007 | $0.00250 |
| Sonnet 5 | $0.00003 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
changelog 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 2d ago.
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.
What it actually says
Deep Wiki: Changelog Generation
Analyze the git commit history of this repository and generate a structured changelog.
Source Repository Resolution (MUST DO FIRST)
Before generating any changelog, 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, link commit hashes:[abc1234](REPO_URL/commit/abc1234) - Local → use plain commit hashes
- Remote URL → store as
- Do NOT proceed until resolved
Process
- Examine recent git commits (messages, dates, authors)
- Group by date: daily for last 7 days, aggregated weekly for older
- Classify each commit into categories
- Generate concise, user-facing descriptions using project terminology from README
Categories
| Emoji | Category | Signal Keywords |
|---|---|---|
| 🆕 | New Features | feat, add, new, implement, introduce |
| 🐛 | Bug Fixes | fix, bug, patch, resolve, hotfix |
| 🔄 | Refactoring | refactor, restructure, reorganize, clean |
| 📝 | Documentation | docs, readme, comment, jsdoc, docstring |
| 🔧 | Configuration | config, env, setting, ci, build |
| 📦 | Dependencies | deps, upgrade, bump, package, lock |
| ⚠️ | Breaking Changes | breaking, BREAKING, migrate, deprecate |
Output
For each time period, output:
## [Date or Date Range]
**[Summary Title]**
[1-2 sentence overview]
### 🆕 New Features
- [Change description]
### 🐛 Bug Fixes
- [Change description]
### ⚠️ Breaking Changes
- [Change description with migration notes]
Focus on user-facing changes. Merge related commits. Highlight breaking changes prominently.
$ARGUMENTS
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.
- 2d ago First seen · 62 lines · 14 tokens per session scan A 43d7a01289aa
changelog is a command published in the GitHub repository microsoft/skills (2,992 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 500 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
pre-commit-check
Tu es un assistant de qualité code. Tu dois effectuer toutes les vérifications nécessaires AVANT de créer un commit, pour garantir que le code respecte les standards du projet.
smart-commit
Generate and create a commit with a conventional commit message based on staged changes.
new-feature-branch
Branch-from-fresh-main boilerplate — checkout main, pull, create branch with a meaningful name, push empty so it can be protected.
commit-and-create-mr
Commit and create MR on Gitlab.
compush
Command "compush" from Insight-Services-APAC/ingenious, covering prompt: generate, commit, and push with git, instructions, examples, single commit (small changes) and multiple commits (extensive changes).
checklist
Generate a custom checklist for the current feature based on user requirements.