What is Copilot-M365-Insights CLAUDE.md?

A set of Claude Code instructions for a project that collects Microsoft Copilot Studio data from Microsoft 365 APIs and CSV exports, stores it in SQLite, and creates Excel reports.

Running data synchronisation, importing Viva analytics CSV files, exporting workbooks, and deploying the project's MCP server to Azure Container Apps.

It tells the coding agent how to set up the project, fetch data, import exports, and produce reports consistently.

How syokiel/Copilot-M365-Insights configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to syokiel/Copilot-M365-Insights. 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/syokiel/Copilot-M365-Insights/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/syokiel/Copilot-M365-Insights

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/syokiel/copilot-m365-insights/claude-md/github.svg)](https://agentmods.dev/instructions/syokiel/copilot-m365-insights/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/syokiel/copilot-m365-insights/claude-md"><img src="https://agentmods.dev/badge/instructions/syokiel/copilot-m365-insights/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/syokiel/copilot-m365-insights/claude-md"><img src="https://agentmods.dev/badge/instructions/syokiel/copilot-m365-insights/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,724 This file is loaded in full into every session.

When invoked 1,724 The same file — it is already loaded in full.

Security scan B 1 finding. 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	$0.01724	$0.01724
Opus 5.5	$0.00690	$0.00690
Sonnet 5.5	$0.00345	$0.00345
Haiku 4.5	$0.00172	$0.00172

Measured 1mo ago against content hash 5d7cf142ba4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

Copilot-M365-Insights CLAUDE.md scanned grade B with 1 finding 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 1mo 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

**MCP server** (`src/mcp_server/server.py`) is transport-dual: stdio when launched locally via `.mcp.json`, HTTP/SSE when deployed to Azure Container Apps via the Dockerfile CMD. In the deployed case it downloads the SQL

CLAUDE.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 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.

What this is

Governance and telemetry reporting for Microsoft Copilot Studio agents across an M365 tenant. Pulls data from ~12 Azure/M365 APIs plus manual CSV exports, stores everything in a local SQLite database, and outputs a multi-sheet Excel workbook. Also exposes an MCP server (stdio locally, HTTP on Azure Container Apps) so AI agents can query the telemetry conversationally, and a Bot Framework conversational agent (src/agent/) that consumes that MCP server.

Commands

# Setup
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

# Fetch all sources + export workbook
python -m src.main all

# Fetch only (no export)
python -m src.main sync

# Export last sync to Excel (no new fetch)
python -m src.main export

# Import Copilot Studio analytics CSVs from a Viva export folder
python -m src.main import-viva <path/to/csv/folder>

# Multi-tenant: point at a different .env (must be the first two args)
python -m src.main --env .env.<tenant> all

# Deploy MCP server to Azure Container Apps
bash deploy.sh deploy-config/<tenant>.env

# One-time tenant provisioning (run in order)
bash provision/step1_insights.sh   # Log Analytics + App Insights
bash provision/step2_identity.sh   # sync SP permissions + admin consent
bash provision/step3_mcp.sh        # register MCP server app in Entra ID

There is no test suite, linter, or type-checker configured in this repo (no tests/, pyproject.toml, or pytest.ini) — don't assume pytest or ruff commands work.

Architecture

Pipeline shape: fetchers/ (one module per data source) → store/ (SqliteStore = per-domain mixins over _base.py; DDL/views in _schema.py; one SQLite DB per tenant kept across runs) → writers/ (one module per Excel sheet, reads back from the store) → workbook_writer.py assembles the final .xlsx. src/main.py orchestrates sync (fetch+store) and export (store+write) as separate phases — all just runs both.

Read the full file on GitHub · 73 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.

1mo ago Changed · +3 lines · +153 tokens per session 5d7cf142ba4b
2mo ago First seen · 70 lines · 1,571 tokens per session scan B 257b257e0e5d

Subscribe to this mod's changes

Copilot-M365-Insights CLAUDE.md is an instructions file published in the GitHub repository syokiel/Copilot-M365-Insights (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,724 tokens to every session, about $0.0069 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics

Copilot-M365-Insights CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Copilot-M365-Insights CLAUDE.mdsyokiel/Copilot-M365-Insights	Instructions file	0	1mo ago	MIT	B	1,724	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	yesterday	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

Copilot-M365-Insights: Instructions file for Claude Code