agentmods.dev

agent365-skills: Instructions file for Claude Code

AGENTS.md

agent365-skills AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from microsoft/agent365-skills. It costs 8,300 tokens per session, scanned A, original, MIT.

Development guidelines for a plugin that configures Microsoft Agent 365 agents. Agent 365 is Microsoft's platform for registering, connecting, observing, and publishing agents.

In plain words
What is it for?
Use them when changing the plugin's seven skills, including setup, Teams publishing, agent registration, tool connections, observability, validation, and local testing.
Why use it?
They provide the available commands, trigger phrases, file format, and platform behavior in one place.

Instructions file for Claude CodeCodexOpenCode ✓ vendor

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT} variable, but also the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; names the AskUserQuestion tool.

This is microsoft/agent365-skills's own configuration. It tells Claude Code, Codex and OpenCode how to work on agent365-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent365-skills configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 50repo changed 20d ago A scan 8,300 tokens original MIT
View source ↗ microsoft/agent365-skills
About the project

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.

microsoft/agent365-skills · 50 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/agent365-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/microsoft/agent365-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/microsoft/agent365-skills

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for agent365-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/microsoft/agent365-skills/agents-md/github.svg)](https://agentmods.dev/instructions/microsoft/agent365-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/microsoft/agent365-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/agent365-skills/agents-md/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.

agentmods 80×15 button for agent365-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/microsoft/agent365-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/microsoft/agent365-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,300 This file is loaded in full into every session.
When invoked 8,300 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08300 $0.08300
Opus 5.5 $0.03320 $0.03320
Sonnet 5.5 $0.01660 $0.01660
Haiku 4.5 $0.00830 $0.00830

Measured 20d ago against content hash 3f8c09462cf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent365-skills AGENTS.md 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.

AGENTS.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent 365 Plugin — Development Guidelines

This file documents conventions for contributors working on the agent365 plugin skills. Read this before making any changes to skill files.

Plugin Purpose

This plugin instruments and configures A365 agents. It contains eight skills:

Skill Command Trigger
make-ai-teammate /agent365:make-ai-teammate "make this agent an AI Teammate", "add AI Teammate hosting", "transform agent to Teams agent"
a365-setup /agent365:a365-setup "run a365 setup", "create blueprint", "register agent"
make-a365-agent /agent365:make-a365-agent "provision agent with a365", "Registration setup", "observability setup", "register this agent"
add-workiq-tools /agent365:add-workiq-tools "add workiq tools", "add MCP servers to this agent"
instrument-observability /agent365:instrument-observability "instrument observability", "add a365 observability"
a365-code-validator /agent365:a365-code-validator "validate a365 code", "debug MAC activity", "check A365 exporter flags"
purview-dlp-integration /agent365:purview-dlp-integration "add purview dlp", "block credit cards/PII before the LLM", "add data loss prevention to my agent"
test-local /agent365:test-local "test this agent locally", "open agentsplayground"

Supported languages for make-ai-teammate: .NET (AgentFramework · Semantic Kernel) · Node.js (LangChain · OpenAI Agents SDK · Claude SDK · Semantic Kernel · Google ADK) · Python (AgentFramework · LangChain · OpenAI · Claude · Semantic Kernel · Google ADK)

Supported languages for instrument-observability: .NET AgentFramework · Node.js (LangChain · OpenAI · Claude SDK · Semantic Kernel · Google ADK) · Python (AgentFramework · LangChain · OpenAI · Claude · Semantic Kernel · Google ADK)

Supported agent stacks for add-workiq-tools (verified against Agent365-{dotnet,python,nodejs}):

  • .NET: Agent Framework · Semantic Kernel (different API: AddToolServersToAgentAsync, not GetMcpToolsAsync) · Azure AI Foundry (best-effort — package published, no Microsoft sample)
  • Node.js: LangChain (returns new agent — capture return) · OpenAI Agents SDK (mutates in place) · Claude SDK (first arg is Options, mutates in place) · ⚠ Semantic Kernel and Google ADK hard-stop (no Microsoft adapter — skill exits at Phase 0B)
  • Python: Agent Framework (uses turn_context= kwarg, requires initial_tools=[]) · OpenAI Agents SDK (uses context= kwarg, no agentic_app_id) · Google ADK (passes agentic_app_id, wraps in asyncio.wait_for) · Semantic Kernel and Azure AI Foundry (best-effort — package published, no Microsoft sample) · ⚠ LangChain / Claude SDK / CrewAI hard-stop (no Microsoft adapter; Claude and CrewAI samples ship a local DIY mcp_tool_registration_service.py scaffold — out of scope for this skill)

Read the full file on GitHub · 376 lines

Changes

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.

  1. 20d ago Changed · -9 tokens per session 3f8c09462cf0
  2. 1mo ago Changed · +2 lines · +508 tokens per session 0342e66a6575
  3. 1mo ago Changed · +14 lines · +730 tokens per session 94bdc0023f46
  4. 2mo ago First seen · 360 lines · 7,071 tokens per session scan A f1535bc95448

Subscribe to this mod's changes

agent365-skills AGENTS.md is an instructions file published in the GitHub repository microsoft/agent365-skills (50 stars, last pushed 16d ago), licensed MIT. It adds 8,300 tokens to every session, about $0.0332 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 2026-08-30.

Building agents
Related

agent365-skills AGENTS.md compared with instructions from other repositories

agent365-skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent365-skills AGENTS.mdmicrosoft/agent365-skillsInstructions file5016d agoMITA8,300Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode