What is openclaw-a365 CLAUDE.md?

A project guide for OpenClaw A365, a plugin that connects an AI agent to Microsoft 365 services such as Teams, Outlook, calendars, email, and users. It includes Docker, CLI, authentication, and Microsoft Graph setup information.

Use it when developing or operating the OpenClaw A365 plugin, including Docker deployment, model configuration, Bot Framework messaging, or Microsoft Graph operations.

It gives agents the project context and commands needed to build, run, configure, and troubleshoot the Microsoft 365 connection.

How SidU/openclaw-a365 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SidU/openclaw-a365. 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/SidU/openclaw-a365/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/SidU/openclaw-a365

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sidu/openclaw-a365/claude-md/github.svg)](https://agentmods.dev/instructions/sidu/openclaw-a365/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sidu/openclaw-a365/claude-md"><img src="https://agentmods.dev/badge/instructions/sidu/openclaw-a365/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sidu/openclaw-a365/claude-md"><img src="https://agentmods.dev/badge/instructions/sidu/openclaw-a365/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,160 This file is loaded in full into every session.

When invoked 1,160 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.

Model	Per session	Once invoked
Fable 5.1	$0.01160	$0.01160
Opus 5.5	$0.00464	$0.00464
Sonnet 5.5	$0.00232	$0.00232
Haiku 4.5	$0.00116	$0.00116

Measured 2mo ago against content hash c02c5300e504, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openclaw-a365 CLAUDE.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 2mo 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.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

OpenClaw A365 is a Microsoft 365 Agents (A365) channel plugin for OpenClaw. It provides native integration with Microsoft 365 through the Bot Framework and Graph API, allowing agents to:

Receive/send messages through Microsoft 365 Agents (Teams, Outlook)
Perform calendar, email, and user operations via Microsoft Graph API
Authenticate as an agentic identity (its own service account, not on-behalf-of-user)

Build and Run Commands

Development with Docker Compose (recommended):

docker-compose up -d        # Build from source and run
docker-compose logs -f      # View logs
docker-compose down         # Stop

Run pre-built image:

docker run --cap-add=NET_ADMIN --env-file .env -p 3978:3978 ghcr.io/sidu/openclaw-a365:latest

OpenClaw CLI commands (inside container or local dev):

pnpm openclaw doctor --fix              # Validate/fix configuration
pnpm openclaw models set <model>        # Set primary model
pnpm openclaw models fallbacks add <m>  # Add fallback model
pnpm openclaw models status             # Check model configuration
pnpm openclaw gateway                   # Start the gateway
pnpm openclaw plugins install .         # Install plugin from current dir
pnpm openclaw plugins enable a365       # Enable A365 plugin

Note: There is no explicit test runner configured. Test files exist (src/*.test.ts) but are designed for the OpenClaw test framework.

Architecture

Core Components

File	Purpose
`index.ts`	Plugin entry point - exports `plugin` object that registers with OpenClaw
`src/channel.ts`	Channel plugin implementation - registers with OpenClaw, provides capabilities
`src/monitor.ts`	Bot Framework webhook listener - receives A365 messages on port 3978
`src/token.ts`	Token management - T1/T2/Agent token flow, in-memory cache
`src/graph-tools.ts`	Graph API tools for LLM - calendar, email, user operations
`src/outbound.ts`	Sends messages back to Bot Framework
`src/conversation-store.ts`	Persists conversation references for proactive messaging
`src/types.ts`	TypeScript types and config schemas

Read the full file on GitHub · 99 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.

2mo ago First seen · 99 lines · 1,160 tokens per session scan A c02c5300e504

Subscribe to this mod's changes

openclaw-a365 CLAUDE.md is an instructions file published in the GitHub repository SidU/openclaw-a365 (133 stars, last pushed 7mo ago), licensed MIT. It adds 1,160 tokens to every session, about $0.0046 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.

Backend and APIs

openclaw-a365 CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openclaw-a365 CLAUDE.mdSidU/openclaw-a365	Instructions file	133	7mo ago	MIT	A	1,160	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

openclaw-a365: Instructions file for Claude Code