Microsoft Agent 365 Skills is a collection of coding-agent skills and MCP configuration for building and operating AI Teammates hosted in Microsoft Teams. It supports the Agent 365 lifecycle, including WorkIQ integration, registration, observability, validation, and local testing, for users of Claude Code and GitHub Copilot.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add microsoft/agent365-skills/plugin install agent365Wrote 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/agent365-skills/make-a365-agent)<a href="https://agentmods.dev/skills/microsoft/agent365-skills/make-a365-agent"><img src="https://agentmods.dev/badge/skills/microsoft/agent365-skills/make-a365-agent.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 | $0.00120 | $0.04892 |
| Opus 5 | $0.00060 | $0.02446 |
| Sonnet 5 | $0.00024 | $0.00978 |
| Haiku 4.5 | $0.00012 | $0.00489 |
Grade C, and why
make-a365-agent scanned grade C with 2 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| Linux | `curl -sL https://aka.ms/DevTunnelCliInstall | bash` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Linux | `curl -sL https://aka.ms/DevTunnelCliInstall | bash` | How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make A365 Agent
Trigger phrases — any of these will activate this skill:
- "provision this agent with agent 365"
- "register this agent"
- "make this agent findable in the Agent 365 catalog"
- "Registration setup for this agent"
- "make this a custom engine agent"
- "run a365 setup all"
- "create a365 blueprint for this agent"
- "set up this agent for observability only"
What this skill does: Provisions your agent with Agent 365 — creates the Blueprint and Entra ID permissions. After setup, always offers observability (instrument-observability) and WorkIQ tools (add-workiq-tools) as optional add-ons.
This skill is normally called from
a365-setupafter CLI verification and Azure prerequisites are confirmed. It can also be invoked directly when those steps are done.
YOUR FIRST ACTION: Load context (Phase 0), then create all todos before running anything.
Phase 0 — Load Context
Show the user a visible task checklist BEFORE Phase 1 work begins. This skill has no per-phase
TaskCreatecalls in the body — derive the checklist from the phase headers (## Phase 0 — Load Context,## Phase 1 — Collect Provisioning Inputs,## Phase 2 — Register with Agent 365, etc.). Exactly one item in_progress at a time; complete before moving on.
- Claude Code: call
TaskCreateonce per phase header (already inallowed-tools); the list renders natively. UseTaskUpdateto flip statuses.- VS Code Copilot Chat / GitHub Copilot CLI:
allowed-toolsis ignored — emit a markdown checklist directly in chat (- [ ] Load context…,- [ ] Collect provisioning inputs…, etc.) and edit items to- [x]as each phase completes.
Check for context passed from a365-setup. If this skill was invoked by a365-setup,
the session already has capabilities, agentStack, programmingLanguage, and
usesTeamsOrCopilot set. Load those values directly.
If invoked directly (no session context):
- Read
.a365-workspace-detection.local.jsonif it exists anddetectedAtis within 60 minutes. LoadagentStack,programmingLanguage, andusesTeamsOrCopilotfrom it.
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.
- 6d ago First seen · 379 lines · 120 tokens per session scan C 54ce3509a04e
make-a365-agent is a skill published in the GitHub repository microsoft/agent365-skills (36 stars, last pushed 10d ago), licensed MIT. It adds 120 tokens to every session and 4,892 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…