Microsoft Agent Framework is a multi-language framework for building, coordinating, and running AI agents and workflows in Python and .NET. Teams use it for agent systems that need orchestration, collaboration, durability, observability, governance, or human involvement beyond a single prompt or chat loop. Catalogue add-ons provide skills and instructions for working with the framework.
Borrowing it
Nothing to install: this file belongs to microsoft/agent-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/agent-framework/main/.github/skills/community-projects/SKILL.mdgit clone --depth 1 https://github.com/microsoft/agent-frameworkWrote 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/skills/microsoft/agent-framework/community-projects)<a href="https://agentmods.dev/skills/microsoft/agent-framework/community-projects"><img src="https://agentmods.dev/badge/skills/microsoft/agent-framework/community-projects/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/agent-framework/community-projects"><img src="https://agentmods.dev/badge/skills/microsoft/agent-framework/community-projects.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.01412 |
| Opus 5.5 | $0.00010 | $0.00565 |
| Sonnet 5.5 | $0.00005 | $0.00282 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
community-projects 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Community Project Catalog Review
Use this skill when reviewing either SDK catalog:
Also use it when an issue or pull request proposes adding an external project, even if neither catalog file has changed yet.
The Agent Framework team syncs these source catalogs to the Microsoft Learn documentation repository. Contributors should make catalog changes in this repository rather than editing the synced copies directly.
Required disclaimer
Each catalog must include this disclaimer before its first project table:
[!IMPORTANT] The projects on this page are created and maintained outside the Microsoft Agent Framework team. Microsoft doesn't own, test, or support these projects. Listing a project doesn't imply Microsoft endorsement or confirm compatibility with any Agent Framework version. For compatibility information, support, and issue handling, contact the project maintainer through the project's repository and issue tracker. For security concerns, follow the maintainer's security reporting guidance.
Catalog structure
- Organize entries only by their primary Agent Framework component:
Model providers,Agent services,Tools,Context providers,Vector stores,Middleware,Evaluation, orUI. - Do not add a provider-based view or group entries by company or service.
- Include only component sections that contain at least one eligible project.
- Use a project in one primary component only. Mention secondary scenarios in
the
Scenarioscell instead of duplicating the row. - Every table must have exactly these columns, in this order:
Name,Brief description,Scenarios,Project,Issues. - Sort rows alphabetically by project name within each component.
Eligibility requirements
An entry is eligible only when all of these checks pass:
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.
- 12d ago Changed · +4 lines 3a255203d9fe
- 19d ago First seen · 143 lines · 26 tokens per session scan A 2fd715b1b21c
community-projects is a skill published in the GitHub repository microsoft/agent-framework (14,368 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,412 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
fabric-spec
Starts a persistent Pi Fabric spec supervisor that audits the main session against a feature design spec and steers only when a requirement lacks verified evidence. Use for strict, unblocked spec compliance while the main agent keeps full freedom to orchestrate.
fabric-swarm
Creates a self-organizing team of persistent Pi Fabric actors with durable topics, mailboxes, and compare-and-swap tasks. Use for messenger-like collaboration and long-lived delegated work.
fabric-advisor
Starts a persistent Pi Fabric peer advisor that reviews the main agent at decision points and surfaces only concrete, material advice. Use for ambient correctness review without another extension.
squads-cli
Squads CLI — operate your squads through the loop; intent in, reviewed work out. TRIGGER when running squads, dispatching agents, triaging the inbox, reading/writing memory, recording feedback, or checking status/usage.
gh
You have access to gh (GitHub CLI) for repository and project management.
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…