What is copilot-for-m365-readiness?

A preparation guide for deploying Microsoft 365 Copilot, Microsoft's AI assistant for work documents and conversations. It covers SharePoint, OneDrive, Teams permissions, labels, and data-loss controls.

Use it to find overshared content, improve sensitivity-label coverage, set Copilot data-loss policies, restrict content discovery, and plan a phased launch.

It helps prevent Copilot from showing sensitive files to people who should not have access. It organizes the security checks needed before a staged rollout.

copilot-for-m365-readiness — Skill for Claude Code and Codex by vinaya

Install

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.

Any agent

npx skills add vinayaklatthe/microsoft-security-skills --skill copilot-for-m365-readiness

Clone the repo

git clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skills

Made for: Claude Code, Codex.

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/skills/vinayaklatthe/microsoft-security-skills/copilot-for-m365-readiness/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/copilot-for-m365-readiness)

Your own site

<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/copilot-for-m365-readiness"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/copilot-for-m365-readiness/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/skills/vinayaklatthe/microsoft-security-skills/copilot-for-m365-readiness"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/copilot-for-m365-readiness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 213 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,988 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00213	$0.01988
Opus 5	$0.00106	$0.00994
Sonnet 5	$0.00043	$0.00398
Haiku 4.5	$0.00021	$0.00199

Measured 12d ago against content hash d5a8759fdb0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

copilot-for-m365-readiness 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 12d 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.

skills/copilot-for-m365-readiness/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft 365 Copilot — Safe Readiness

Microsoft 365 Copilot is only as safe as your SharePoint, OneDrive, and Teams permission hygiene. The #1 incident pattern is "Copilot surfaced HR/board/legal content because the underlying site was over-permissioned." This skill is the end-to-end readiness playbook — identify oversharing, contain via SAM and labels, then enable Copilot in waves.

When to use

Preparing to deploy Microsoft 365 Copilot. Use for the pre-launch security workstream: oversharing detection, containment controls, label/DLP coverage, audit, and phased rollout.

Do not use this skill for the broader oversharing program (m365-oversharing), Purview DSPM for AI in isolation (purview-dspm-ai), or agent-specific security (microsoft-agent-365).

Readiness gates — don't skip

Gate	Why
Sensitivity labels published and adopted	Copilot honors label encryption + usage rights
Auto-labeling for known sensitive content classes	Catches the long tail users won't label
DLP for Copilot policies	Prevents sensitive content surfacing in chat answers
SAM (SharePoint Advanced Management) provisioned	Required for restricted access + data access governance
Site ownership confirmed	Orphaned sites with permissive ACLs are the #1 incident path
Audit on	Copilot interactions are auditable; off = no investigation possible

Approach

Inventory and triage oversharing. Run SAM Data Access Governance reports:
- Sites shared with Everyone except external users (EEEU).
- Sites with anonymous links.
- Sites with high external sharing volume.
- Sites with sensitive content but permissive ACLs. Prioritize the top 5% by volume and sensitivity.
Apply Restricted SharePoint Search (RSS) as an interim safeguard. RSS limits Copilot grounding (and SharePoint search) to a curated allowlist of sites + the user's own OneDrive. Buys 90 days while you fix the long tail. Verify: in test tenant, Copilot prompt "summarize HR salary data" returns no grounded content from non-allowlisted sites.

Read the full file on GitHub · 144 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.

12d ago First seen · 144 lines · 213 tokens per session scan A d5a8759fdb0b

Subscribe to this mod's changes

copilot-for-m365-readiness is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 213 tokens to every session and 1,988 once invoked, about $0.0011 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.

Security ai-agents copilot defender entra entra-id microsoft

power-automate

Use when operating Microsoft Power Automate cloud flows from code — create, enable, update, list or delete via the Dataverse Web API (workflow table, category 5) with Entra ID OAuth2, plus run-history debugging. NOT designing the flow definition (that is automation-flows), NOT picking a platform by billing model (that…

ericrisco/rsc-harness · 82 tokens

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…

microsoft/vscode · 72 tokens

copilot-for-m365-readiness