Microsoft 365 Agents SDK is a software toolkit for building AI agents that can communicate through channels such as Microsoft 365 Copilot, Teams, web apps, and custom applications. Developers use it to add state, storage, event handling, and channel-specific behavior while choosing their own AI services and models. The catalogue entries are skills and plugins for working with this SDK.
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 skills add microsoft/Agents --skill teams-app-manifestgit clone --depth 1 https://github.com/microsoft/AgentsWrote 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/agents/teams-app-manifest)<a href="https://agentmods.dev/skills/microsoft/agents/teams-app-manifest"><img src="https://agentmods.dev/badge/skills/microsoft/agents/teams-app-manifest/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/agents/teams-app-manifest"><img src="https://agentmods.dev/badge/skills/microsoft/agents/teams-app-manifest.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 | $0.00072 | $0.02535 |
| Opus 5.5 | $0.00029 | $0.01014 |
| Sonnet 5.5 | $0.00014 | $0.00507 |
| Haiku 4.5 | $0.00007 | $0.00253 |
Grade A, and why
teams-app-manifest 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 20d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teams App Manifest
Create the smallest released Teams app manifest that accurately declares the application's implemented and intended Teams capabilities. Keep evidence for capability decisions during the work, but report only user-relevant results. Stop instead of guessing security-sensitive or product-intent values.
For new samples in this repository, place the manifest and its icons in manifest/. When completing an existing package, preserve its directory unless repository policy calls for a rename; keep documentation and package configuration aligned with the actual path.
When documenting package creation or upload, verify the commands against the current CLI documentation. Do not assume a CLI command creates a ZIP in the manifest directory; a manually created package must place manifest.json and its referenced icons at the ZIP root.
This is a standalone skill for Agents SDK source. Treat caller-provided requirements and repository policy as input, but derive manifest decisions only from the authority order and evidence rules in this skill.
Execution and response contract
If the caller provides manifest-schema inspection and validation tools, use them for the checks below instead of requiring shell execution. Preserve their exact diagnostics and validate the final manifest before claiming success. A read-only reviewer inspects and reports corrections without writing the manifest.
An explicit invocation of this skill with an application or source path is a request to process that application. Unless the user explicitly requests review, audit, or no changes, inspect the source and immediately perform Generate or Complete mode. Do not stop after inspection.
Generate and Complete have only two user-visible phases:
- Blocking questions, only when required: Resolve values from repository evidence, caller policy, safe defaults, and approved placeholders first. If a decision still blocks an accurate manifest, ask all currently known blocking questions together. Ask direct questions only; do not return an inspection report, findings summary, capability plan, proposed mode, or implementation plan. After the user answers, resume the same workflow without repeating the findings.
- One final manifest report: Create or update the manifest, perform the required local validation, then return one report using manifest-evidence.template.md. Report only added or changed manifest behavior, a short validation result, and actionable user input. Do not expose the internal capability plan or return a preliminary report before writing the manifest.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/base-manifest.template.json 639 B
- assets/manifest-evidence.template.md 754 B
- references/authentication-and-permissions.md 4.0 KB
- references/bots.md 11 KB
- references/capability-ledger.md 3.3 KB
- references/capability-sources.md 29 KB
- references/cards-and-dialogs.md 2.3 KB
- references/meetings.md 3.6 KB
- references/message-extensions.md 2.8 KB
- references/schema-validation.md 5.5 KB
- references/source-detection.md 5.2 KB
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.
- 20d ago First seen · 139 lines · 72 tokens per session scan A 07ac8afb39fb
teams-app-manifest is a skill published in the GitHub repository microsoft/Agents (1,085 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 2,535 once invoked, about $0.0003 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 2026-09-26.
Other skills, from other repositories
azure-kusto-graph
Build and query Kusto graphs from natural language. Covers transient graphs (make-graph), persistent graph models/snapshots, pattern matching (graph-match), shortest paths, connected components, and graph-to-table export. Generates the edges-first thinking: define edges, define node lookups, union, make-graph. WHEN…
azure-kusto-irql-graph
Apply IRQL graph functions to KQL or IRQL query results for Kusto Explorer visualization. Generates LiftToGraph mappings and composes GraphRenderView, GraphFoldByProperty, ExtractNode, EnrichNode, and EnrichGraph calls. Accepts a supplied query or limited basic natural-language source request; it is not a general…
azure-maps-search-dotnet
Azure Maps SDK for .NET. Location-based services including geocoding, routing, rendering, geolocation, and weather. Use for address search, directions, map tiles, IP geolocation, and weather data. Triggers: "Azure Maps", "MapsSearchClient", "MapsRoutingClient", "MapsRenderingClient", "geocoding .NET", "route…
azure-resource-manager-postgresql-dotnet
Azure PostgreSQL Flexible Server SDK for .NET. Database management for PostgreSQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "PostgreSQL", "PostgreSqlFlexibleServer", "PostgreSQL Flexible Server", "Azure Database for…
azure-identity-py
Azure Identity SDK for Python authentication with Microsoft Entra ID. Use for DefaultAzureCredential, managed identity, service principals, and token caching. Triggers: "azure-identity", "DefaultAzureCredential", "authentication", "managed identity", "service principal", "credential".
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.