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 agentmods add skills/microsoft/agents/bf-to-agents-sdk-typescript-migrationnpx skills add microsoft/Agents --skill bf-to-agents-sdk-typescript-migrationgit 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/bf-to-agents-sdk-typescript-migration)<a href="https://agentmods.dev/skills/microsoft/agents/bf-to-agents-sdk-typescript-migration"><img src="https://agentmods.dev/badge/skills/microsoft/agents/bf-to-agents-sdk-typescript-migration.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 | $0.00071 | $0.01011 |
| Opus 5 | $0.00036 | $0.00505 |
| Sonnet 5 | $0.00014 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
bf-to-agents-sdk-typescript-migration 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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BotBuilderJS to Agents SDK migration
Target AgentApplication and preserve observable behavior. Always assess and report before editing. Use migration-map.md as the primary reference; search it for each detected package, class, method, property, or handler.
Workflow
- Inspect the bot's packages, imports, entry points, handlers, state, middleware, hosting, authentication, tests, and deployment files.
- Inventory every Bot Framework symbol and behavior. Classify each item with the migration map:
- Direct: replace the package or API while preserving the design.
- Rewrite: implement the supported
AgentApplicationpattern. - Decision: verified SDK-supported choices exist, but the user must select one.
- Unsupported: no verified stable Agents SDK for JavaScript equivalent exists.
- Produce the migration plan in the format below. Do not edit project code during this assessment phase.
- Stop and ask which numbered Direct and Rewrite items to implement and which Decision choices to make. Exclude Unsupported items from implementation.
- After explicit selection, confirm the assessed files, dependencies, and scope have not changed. If they changed, refresh the plan and obtain a new selection. Otherwise, implement only the selected items and update the lockfile.
- Run the project's build/type-check, lint, and tests. Start the service and exercise the message endpoint and affected custom, invoke, storage, and proactive paths when possible.
- Report migrated items, decisions still required, unsupported behavior left unchanged, and validation results.
If multiple bots are present and scope is unclear, ask which bot to assess before step 2.
Rules
- Do not invent an SDK API, shim, placeholder, or unrelated replacement to make the migration appear complete. Mark behavior without a verified stable target as Unsupported.
- Treat the migration map as candidate mappings. Verify every Direct and Rewrite target against declarations for the exact stable package version planned for the project. Repository-main code and official samples may identify candidates but do not prove stable availability; repo-only or
@nextfunctionality is Decision, and functionality with no verified package target is Unsupported. - Leave Unsupported code and its dependencies unchanged. Discuss a replacement only as a separate modernization decision, never as an Agents SDK migration mapping.
- Implement a Decision item only after the user selects a verified SDK-supported option.
- Preserve exports, module system, endpoint paths, middleware order, route precedence, invoke responses, state keys, storage identifiers, OAuth connection names, and Teams command IDs unless the user approves a change.
AgentApplicationselects the first matching route. Put specific routes before catch-alls and merge behavior that previously chained throughnext().- Remove a Bot Framework dependency only when no retained import or runtime use remains. Unsupported code and dependencies always remain unchanged within this skill. Decision code keeps its dependency until the user selects a verified supported migration; deletion or isolation is a separate task outside this skill.
- Prefer compatible stable package versions and preserve the package manager. Classify functionality available only in
@nextas Decision and ask before using it. - Keep production authentication enabled and never expose secrets.
- Change only what is necessary to install, build, test, and run the selected migration items.
What ships with it
1 file 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.
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.
- 5d ago First seen · 63 lines · 71 tokens per session scan A aaf345acb013
bf-to-agents-sdk-typescript-migration is a skill published in the GitHub repository microsoft/Agents (1,056 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,011 once invoked, about $0.0004 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 2026-08-30.
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-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".
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-mgmt-apicenter-dotnet
Azure API Center SDK for .NET. Centralized API inventory management with governance, versioning, and discovery. Use for creating API services, workspaces, APIs, versions, definitions, environments, deployments, and metadata schemas. Triggers: "API Center", "ApiCenterService", "ApiCenterWorkspace", "ApiCenterApi", "API…
azure-resource-manager-durabletask-dotnet
Azure Resource Manager SDK for Durable Task Scheduler in .NET. Use for MANAGEMENT PLANE operations: creating/managing Durable Task Schedulers, Task Hubs, and retention policies via Azure Resource Manager. Triggers: "Durable Task Scheduler", "create scheduler", "task hub", "DurableTaskSchedulerResource", "provision…